dipanshuk/clickHouseData
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: dipanshuk/clickHouseData:379ead3d8eb1b6743a1cb5e78765f35d3cbc2563
Branches Tags
dipanshuk/clickHouseData:main
..
compare: dipanshuk/clickHouseData:579d59e1b0b5c4d00ac0d18e9b8bb04e50d26bc7
Branches Tags
dipanshuk/clickHouseData:main

2 Commits
379ead3d8e .. 579d59e1b0

Author SHA1 Message Date
Dipanshu Kumar 579d59e1b0 Journey_Plan data Import 2026-05-20 12:40:47 +05:30
Dipanshu Kumar 3be8cd7259 [Web Logins] Import 2026-05-19 16:58:54 +05:30
12 changed files with 25860 additions and 171 deletions
Expand all files Collapse all files
Journey_Plan_Import.py
+321 -171
View File
@@ -1,5 +1,3 @@
import pyodbc import pyodbc
import pandas as pd import pandas as pd
import clickhouse_connect import clickhouse_connect
@@ -7,6 +5,7 @@ import numpy as np
from datetime import datetime from datetime import datetime
import traceback import traceback
import warnings import warnings
import time
# ========================================================= # =========================================================
# IGNORE WARNINGS # IGNORE WARNINGS
@@ -16,10 +15,12 @@ warnings.filterwarnings(
'pandas only supports SQLAlchemy connectable' 'pandas only supports SQLAlchemy connectable'
) )
print("ETL Started :", datetime.now()) print("\n================================================")
print("ETL STARTED :", datetime.now())
print("================================================")
# ========================================================= # =========================================================
# SQL SERVER CONNECTION # SQL SERVER CONNECTION STRING
# ========================================================= # =========================================================
SQL_CONN_STR = ( SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};' 'DRIVER={ODBC Driver 17 for SQL Server};'
@@ -28,6 +29,7 @@ SQL_CONN_STR = (
'UID=bsgteam_test;' 'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;' 'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;' 'TrustServerCertificate=yes;'
'Connection Timeout=60;'
) )
# ========================================================= # =========================================================
@@ -42,11 +44,67 @@ CH_CONFIG = {
} }
# ========================================================= # =========================================================
# TABLE NAME # TABLE DETAILS
# ========================================================= # =========================================================
TABLE_NAME = 'Journey_Plan' TABLE_NAME = 'Journey_Plan'
PROJECT_ID = 41654 PROJECT_ID = 41654
# =========================================================
# SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CHUNK SIZE
# =========================================================
chunk_size = 20000
# =========================================================
# CONNECT SQL SERVER
# =========================================================
def connect_sql():
try:
conn = pyodbc.connect(
SQL_CONN_STR,
autocommit=True
)
print("Connected SQL Server")
return conn
except Exception as e:
print("SQL CONNECTION FAILED")
print(str(e))
raise
# =========================================================
# CONNECT CLICKHOUSE
# =========================================================
def connect_clickhouse():
try:
client = clickhouse_connect.get_client(
**CH_CONFIG
)
print("Connected ClickHouse")
return client
except Exception as e:
print("CLICKHOUSE CONNECTION FAILED")
print(str(e))
raise
# ========================================================= # =========================================================
# CLEAN DATAFRAME # CLEAN DATAFRAME
# ========================================================= # =========================================================
@@ -66,39 +124,46 @@ def clean_dataframe(df):
try: try:
col_lower = col.lower() print(f"\nCleaning Column : {col}")
# ===================================== # =====================================
# DATE COLUMNS # AUTO DETECT DATE / TIME COLUMNS
# ===================================== # =====================================
if 'date' in col_lower: if (
'date' in col.lower()
or 'time' in col.lower()
):
print(f"Cleaning Date Column : {col}") print(f"Date Column : {col}")
df[col] = pd.to_datetime( df[col] = pd.to_datetime(
df[col], df[col],
errors='coerce' errors='coerce'
) )
# Remove invalid dates cleaned_dates = []
df[col] = df[col].where(
(df[col].dt.year >= 1970) &
(df[col].dt.year <= 2100)
)
# Convert to Python Date for val in df[col]:
df[col] = df[col].apply(
lambda x: if pd.isnull(val):
x.date()
if pd.notnull(x) cleaned_dates.append(None)
else None
) else:
cleaned_dates.append(
val.to_pydatetime()
)
df[col] = cleaned_dates
# ===================================== # =====================================
# INTEGER COLUMNS # INTEGER COLUMNS
# ===================================== # =====================================
elif pd.api.types.is_integer_dtype(df[col]): elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric( df[col] = pd.to_numeric(
df[col], df[col],
errors='coerce' errors='coerce'
@@ -116,38 +181,27 @@ def clean_dataframe(df):
# ===================================== # =====================================
elif pd.api.types.is_float_dtype(df[col]): elif pd.api.types.is_float_dtype(df[col]):
non_null = df[col].dropna() print(f"Float Column : {col}")
# --------------------------------- df[col] = pd.to_numeric(
# Convert whole float to int df[col],
# Example: errors='coerce'
# 3240.0 -> 3240 )
# ---------------------------------
if len(non_null) > 0 and (
(non_null % 1 == 0).all()
):
df[col] = df[col].apply( df[col] = df[col].apply(
lambda x: lambda x:
int(x) float(x)
if pd.notnull(x) if pd.notnull(x)
else None else None
) )
else:
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# ===================================== # =====================================
# OBJECT / STRING COLUMNS # OBJECT / STRING COLUMNS
# ===================================== # =====================================
else: else:
print(f"String/Object Column : {col}")
cleaned = [] cleaned = []
for val in df[col]: for val in df[col]:
@@ -157,6 +211,28 @@ def clean_dataframe(df):
cleaned.append(None) cleaned.append(None)
# DATETIME
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# INTEGER # INTEGER
elif isinstance( elif isinstance(
val, val,
@@ -166,7 +242,9 @@ def clean_dataframe(df):
) )
): ):
cleaned.append(int(val)) cleaned.append(
int(val)
)
# FLOAT # FLOAT
elif isinstance( elif isinstance(
@@ -183,41 +261,26 @@ def clean_dataframe(df):
else: else:
# IMPORTANT FIX cleaned.append(
# Avoid '3240.0' string issue float(val)
if val.is_integer(): )
cleaned.append(int(val))
else:
cleaned.append(float(val))
# STRING
elif isinstance(val, str):
cleaned.append(val.strip())
# BOOLEAN # BOOLEAN
elif isinstance(val, bool):
cleaned.append(int(val))
# DATETIME
elif isinstance( elif isinstance(
val, val,
( bool
datetime,
pd.Timestamp
)
): ):
cleaned.append(str(val)) cleaned.append(
int(val)
)
# OTHER # STRING
else: else:
cleaned.append(str(val)) cleaned.append(
str(val).strip()
)
df[col] = cleaned df[col] = cleaned
@@ -247,16 +310,12 @@ try:
# ===================================================== # =====================================================
# CONNECT SQL SERVER # CONNECT SQL SERVER
# ===================================================== # =====================================================
sql_conn = pyodbc.connect(SQL_CONN_STR) sql_conn = connect_sql()
print("Connected to SQL Server")
# ===================================================== # =====================================================
# CONNECT CLICKHOUSE # CONNECT CLICKHOUSE
# ===================================================== # =====================================================
ch_client = clickhouse_connect.get_client(**CH_CONFIG) ch_client = connect_clickhouse()
print("Connected to ClickHouse")
# ===================================================== # =====================================================
# QUERY # QUERY
@@ -267,125 +326,214 @@ try:
WHERE Project_Id = {PROJECT_ID} WHERE Project_Id = {PROJECT_ID}
""" """
print("\nExecuting Query:") print("\nExecuting Query")
print(query) print(query)
# ===================================================== # =====================================================
# CHUNK SIZE # RETRY SETTINGS
# ===================================================== # =====================================================
chunk_size = 100000 retry_count = 0
max_retry = 5
total_rows = 0
# ===================================================== # =====================================================
# READ DATA # MAIN RETRY LOOP
# ===================================================== # =====================================================
for chunk in pd.read_sql( while retry_count < max_retry:
query,
sql_conn,
chunksize=chunk_size
):
try: try:
print("\n================================") # =============================================
print(f"Processing {len(chunk)} Rows") # READ SQL DATA
print("================================") # =============================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
# ================================================= try:
# CLEAN DATA
# =================================================
chunk = clean_dataframe(chunk)
# =================================================
# DEBUG COLUMN TYPES
# =================================================
print("\nCOLUMN TYPES")
for col in chunk.columns:
sample = chunk[col].dropna()
if len(sample) > 0:
print("\n================================")
print( print(
col, f"Processing Rows : "
type(sample.iloc[0]), f"{len(chunk)}"
sample.iloc[0] )
print("================================")
# =====================================
# CLEAN DATA
# =====================================
chunk = clean_dataframe(chunk)
# =====================================
# DEBUG COLUMN TYPES
# =====================================
print("\nCOLUMN DATATYPES")
print(chunk.dtypes)
print("\nCOLUMN SAMPLE TYPES")
for col in chunk.columns:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
# =====================================
# TRUNCATE TABLE FIRST TIME ONLY
# =====================================
if (
TRUNCATE_BEFORE_LOAD
and
not table_truncated
):
print("\n================================")
print(
f"TRUNCATING TABLE : "
f"{TABLE_NAME}"
)
print("================================")
# IMPORTANT FIX
truncate_query = f"""
TRUNCATE TABLE
`{CH_CONFIG['database']}`.`{TABLE_NAME}`
"""
ch_client.command(
truncate_query
)
print(
"TABLE TRUNCATED SUCCESSFULLY"
)
table_truncated = True
# =====================================
# INSERT INTO CLICKHOUSE
# =====================================
print(
"\nINSERTING INTO CLICKHOUSE..."
) )
# ================================================= ch_client.insert_df(
# SAMPLE DATA table=TABLE_NAME,
# ================================================= df=chunk,
print("\nSAMPLE DATA") database=CH_CONFIG['database']
print(chunk.head(2)) )
# ================================================= print(
# INSERT INTO CLICKHOUSE f"INSERTED : "
# ================================================= f"{len(chunk)} ROWS"
print("\nInserting into ClickHouse...") )
ch_client.insert_df( except Exception as insert_error:
table=TABLE_NAME,
df=chunk,
database=CH_CONFIG['database']
)
total_rows += len(chunk) print("\n================================")
print("INSERT FAILED")
print("================================")
print( print(str(insert_error))
f"\nInserted Total Rows : {total_rows}"
)
except Exception as chunk_error: traceback.print_exc()
# =================================
# SAVE ERROR LOG
# =================================
with open(
"insert_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : "
f"{datetime.now()}"
)
log.write(
f"\nTABLE : "
f"{TABLE_NAME}"
)
log.write(
f"\nERROR : "
f"{str(insert_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
# =============================================
# SUCCESS
# =============================================
break
# =================================================
# SQL CONNECTION FAILURE
# =================================================
except pyodbc.OperationalError as op_error:
retry_count += 1
print("\n================================") print("\n================================")
print("CHUNK INSERT FAILED") print(
f"SQL CONNECTION LOST "
f"- RETRY {retry_count}"
)
print("================================") print("================================")
print(str(chunk_error)) print(str(op_error))
time.sleep(10)
try:
sql_conn.close()
except:
pass
# RECONNECT SQL
sql_conn = connect_sql()
# =================================================
# OTHER ERROR
# =================================================
except Exception as loop_error:
print("\n================================")
print("MAIN LOOP ERROR")
print("================================")
print(str(loop_error))
traceback.print_exc() traceback.print_exc()
# ============================================= break
# SAVE ERROR LOG
# =============================================
with open(
"clickhouse_chunk_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nTABLE : {TABLE_NAME}"
)
log.write(
f"\nERROR : {str(chunk_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
print("\n================================") print("\n================================")
print("ETL COMPLETED SUCCESSFULLY") print("ETL COMPLETED SUCCESSFULLY")
print(f"TOTAL ROWS INSERTED : {total_rows}")
print("================================") print("================================")
# ========================================================= # =========================================================
@@ -402,7 +550,7 @@ except Exception as main_error:
traceback.print_exc() traceback.print_exc()
with open( with open(
"clickhouse_main_error.log", "main_error.log",
"a", "a",
encoding="utf-8" encoding="utf-8"
) as log: ) as log:
@@ -437,7 +585,7 @@ finally:
sql_conn.close() sql_conn.close()
print("\nSQL Server Connection Closed") print("\nSQL SERVER CONNECTION CLOSED")
except: except:
pass pass
@@ -446,9 +594,11 @@ finally:
ch_client.close() ch_client.close()
print("ClickHouse Connection Closed") print("CLICKHOUSE CONNECTION CLOSED")
except: except:
pass pass
print("\nETL Finished :", datetime.now()) print("\n================================================")
print("ETL FINISHED :", datetime.now())
print("================================================")
OQaD Import.py
+545
View File
@@ -0,0 +1,545 @@
import pyodbc
import pandas as pd
import clickhouse_connect
import numpy as np
from datetime import datetime
import traceback
import warnings
# =========================================================
# IGNORE WARNINGS
# =========================================================
warnings.filterwarnings(
'ignore',
'pandas only supports SQLAlchemy connectable'
)
print("ETL Started :", datetime.now())
# =========================================================
# SQL SERVER CONNECTION
# =========================================================
SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};'
'SERVER=10.200.25.65;'
'DATABASE=CPMIndiaBusinessInsight;'
'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;'
)
# =========================================================
# CLICKHOUSE CONFIG
# =========================================================
CH_CONFIG = {
'host': '172.188.12.194',
'port': 8123,
'username': 'default',
'password': 'dipanshu_k',
'database': 'DaburIndia_BI'
}
# =========================================================
# TABLE NAME
# =========================================================
TABLE_NAME = 'OQaD'
PROJECT_ID = 41654
# =========================================================
# LOAD SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CLICKHOUSE DATE COLUMNS
# =========================================================
DATE_COLUMNS = [
'visit_date'
]
# =========================================================
# CLICKHOUSE DATETIME COLUMNS
# =========================================================
DATETIME_COLUMNS = [
'create_date',
'update_date'
]
# =========================================================
# CLEAN DATAFRAME
# =========================================================
def clean_dataframe(df):
try:
# ---------------------------------------------
# Replace NaN
# ---------------------------------------------
df = df.replace({np.nan: None})
# ---------------------------------------------
# Process Column Wise
# ---------------------------------------------
for col in df.columns:
try:
print(f"\nCleaning Column : {col}")
# =====================================
# DATE32 COLUMNS
# =====================================
if col.lower() in [
x.lower() for x in DATE_COLUMNS
]:
print(f"Date32 Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
# Remove invalid dates
df[col] = df[col].where(
(df[col].dt.year >= 1970) &
(df[col].dt.year <= 2100)
)
# Convert to datetime.date
df[col] = df[col].apply(
lambda x:
x.date()
if pd.notnull(x)
else None
)
# =====================================
# DATETIME64 COLUMNS
# =====================================
elif col.lower() in [
x.lower() for x in DATETIME_COLUMNS
]:
print(f"DateTime Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
# Remove invalid dates
df[col] = df[col].where(
(df[col].dt.year >= 1970) &
(df[col].dt.year <= 2100)
)
# Convert to datetime.datetime
df[col] = df[col].apply(
lambda x:
x.to_pydatetime()
if pd.notnull(x)
else None
)
# =====================================
# INTEGER COLUMNS
# =====================================
elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
# =====================================
# FLOAT COLUMNS
# =====================================
elif pd.api.types.is_float_dtype(df[col]):
print(f"Float Column : {col}")
non_null = df[col].dropna()
# Convert whole float to int
if len(non_null) > 0 and (
(non_null % 1 == 0).all()
):
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
else:
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# =====================================
# OBJECT / STRING COLUMNS
# =====================================
else:
print(f"String/Object Column : {col}")
cleaned = []
for val in df[col]:
# NULL
if pd.isnull(val):
cleaned.append(None)
# INTEGER
elif isinstance(
val,
(
int,
np.integer
)
):
cleaned.append(int(val))
# FLOAT
elif isinstance(
val,
(
float,
np.floating
)
):
if np.isnan(val):
cleaned.append(None)
else:
if val.is_integer():
cleaned.append(int(val))
else:
cleaned.append(float(val))
# STRING
elif isinstance(val, str):
cleaned.append(val.strip())
# BOOLEAN
elif isinstance(val, bool):
cleaned.append(int(val))
# DATETIME
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# OTHER
else:
cleaned.append(str(val))
df[col] = cleaned
except Exception as col_error:
print("\n================================")
print(f"COLUMN FAILED : {col}")
print(str(col_error))
print("================================")
return df
except Exception as clean_error:
print("\n================================")
print("DATA CLEAN FAILED")
print(str(clean_error))
print("================================")
return df
# =========================================================
# MAIN PROCESS
# =========================================================
try:
# =====================================================
# CONNECT SQL SERVER
# =====================================================
sql_conn = pyodbc.connect(SQL_CONN_STR)
print("Connected to SQL Server")
# =====================================================
# CONNECT CLICKHOUSE
# =====================================================
ch_client = clickhouse_connect.get_client(**CH_CONFIG)
print("Connected to ClickHouse")
# =====================================================
# QUERY
# =====================================================
query = f"""
SELECT *
FROM dbo.[{TABLE_NAME}]
WHERE Project_Id = {PROJECT_ID}
"""
print("\nExecuting Query:")
print(query)
# =====================================================
# CHUNK SIZE
# =====================================================
chunk_size = 100000
total_rows = 0
# =====================================================
# READ DATA
# =====================================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
try:
print("\n================================")
print(f"Processing {len(chunk)} Rows")
print("================================")
# =================================================
# CLEAN DATA
# =================================================
chunk = clean_dataframe(chunk)
# =================================================
# DEBUG COLUMN TYPES
# =================================================
print("\nCOLUMN TYPES")
for col in chunk.columns:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
# =================================================
# DEBUG DATE COLUMN
# =================================================
if 'visit_date' in chunk.columns:
print("\nvisit_date Sample")
print(chunk['visit_date'].head())
sample = chunk['visit_date'].dropna()
if len(sample) > 0:
print(
"visit_date datatype:",
type(sample.iloc[0])
)
# =================================================
# TRUNCATE TABLE FIRST TIME ONLY
# =================================================
if TRUNCATE_BEFORE_LOAD and not table_truncated:
print("\n================================")
print(f"TRUNCATING TABLE : {TABLE_NAME}")
print("================================")
truncate_query = f"""
TRUNCATE TABLE
{CH_CONFIG['database']}.{TABLE_NAME}
"""
ch_client.command(truncate_query)
print("TABLE TRUNCATED SUCCESSFULLY")
table_truncated = True
# =================================================
# INSERT INTO CLICKHOUSE
# =================================================
print("\nInserting into ClickHouse...")
ch_client.insert_df(
table=TABLE_NAME,
df=chunk,
database=CH_CONFIG['database']
)
total_rows += len(chunk)
print(
f"\nInserted Total Rows : {total_rows}"
)
except Exception as chunk_error:
print("\n================================")
print("CHUNK INSERT FAILED")
print("================================")
print(str(chunk_error))
traceback.print_exc()
# =============================================
# SAVE ERROR LOG
# =============================================
with open(
"clickhouse_chunk_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nTABLE : {TABLE_NAME}"
)
log.write(
f"\nERROR : {str(chunk_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
print("\n================================")
print("ETL COMPLETED SUCCESSFULLY")
print(f"TOTAL ROWS INSERTED : {total_rows}")
print("================================")
# =========================================================
# MAIN ERROR
# =========================================================
except Exception as main_error:
print("\n================================")
print("MAIN ERROR")
print("================================")
print(str(main_error))
traceback.print_exc()
with open(
"clickhouse_main_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nERROR : {str(main_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
# =========================================================
# CLOSE CONNECTIONS
# =========================================================
finally:
try:
sql_conn.close()
print("\nSQL Server Connection Closed")
except:
pass
try:
ch_client.close()
print("ClickHouse Connection Closed")
except:
pass
print("\nETL Finished :", datetime.now())
PaidVisibility_Compliance Import.py
+604
View File
@@ -0,0 +1,604 @@
import pyodbc
import pandas as pd
import clickhouse_connect
import numpy as np
from datetime import datetime
import traceback
import warnings
import time
# =========================================================
# IGNORE WARNINGS
# =========================================================
warnings.filterwarnings(
'ignore',
'pandas only supports SQLAlchemy connectable'
)
print("\n================================================")
print("ETL STARTED :", datetime.now())
print("================================================")
# =========================================================
# SQL SERVER CONNECTION STRING
# =========================================================
SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};'
'SERVER=10.200.25.65;'
'DATABASE=CPMIndiaBusinessInsight;'
'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;'
'Connection Timeout=60;'
)
# =========================================================
# CLICKHOUSE CONFIG
# =========================================================
CH_CONFIG = {
'host': '172.188.12.194',
'port': 8123,
'username': 'default',
'password': 'dipanshu_k',
'database': 'DaburIndia_BI'
}
# =========================================================
# TABLE DETAILS
# =========================================================
TABLE_NAME = 'Sales'
PROJECT_ID = 41654
# =========================================================
# SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CHUNK SIZE
# =========================================================
chunk_size = 20000
# =========================================================
# CONNECT SQL SERVER
# =========================================================
def connect_sql():
try:
conn = pyodbc.connect(
SQL_CONN_STR,
autocommit=True
)
print("Connected SQL Server")
return conn
except Exception as e:
print("SQL CONNECTION FAILED")
print(str(e))
raise
# =========================================================
# CONNECT CLICKHOUSE
# =========================================================
def connect_clickhouse():
try:
client = clickhouse_connect.get_client(
**CH_CONFIG
)
print("Connected ClickHouse")
return client
except Exception as e:
print("CLICKHOUSE CONNECTION FAILED")
print(str(e))
raise
# =========================================================
# CLEAN DATAFRAME
# =========================================================
def clean_dataframe(df):
try:
# ---------------------------------------------
# Replace NaN
# ---------------------------------------------
df = df.replace({np.nan: None})
# ---------------------------------------------
# Process Column Wise
# ---------------------------------------------
for col in df.columns:
try:
print(f"\nCleaning Column : {col}")
# =====================================
# AUTO DETECT DATE / TIME COLUMNS
# =====================================
if (
'date' in col.lower()
or 'time' in col.lower()
):
print(f"Date Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
cleaned_dates = []
for val in df[col]:
if pd.isnull(val):
cleaned_dates.append(None)
else:
cleaned_dates.append(
val.to_pydatetime()
)
df[col] = cleaned_dates
# =====================================
# INTEGER COLUMNS
# =====================================
elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
# =====================================
# FLOAT COLUMNS
# =====================================
elif pd.api.types.is_float_dtype(df[col]):
print(f"Float Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# =====================================
# OBJECT / STRING COLUMNS
# =====================================
else:
print(f"String/Object Column : {col}")
cleaned = []
for val in df[col]:
# NULL
if pd.isnull(val):
cleaned.append(None)
# DATETIME
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# INTEGER
elif isinstance(
val,
(
int,
np.integer
)
):
cleaned.append(
int(val)
)
# FLOAT
elif isinstance(
val,
(
float,
np.floating
)
):
if np.isnan(val):
cleaned.append(None)
else:
cleaned.append(
float(val)
)
# BOOLEAN
elif isinstance(
val,
bool
):
cleaned.append(
int(val)
)
# STRING
else:
cleaned.append(
str(val).strip()
)
df[col] = cleaned
except Exception as col_error:
print("\n================================")
print(f"COLUMN FAILED : {col}")
print(str(col_error))
print("================================")
return df
except Exception as clean_error:
print("\n================================")
print("DATA CLEAN FAILED")
print(str(clean_error))
print("================================")
return df
# =========================================================
# MAIN PROCESS
# =========================================================
try:
# =====================================================
# CONNECT SQL SERVER
# =====================================================
sql_conn = connect_sql()
# =====================================================
# CONNECT CLICKHOUSE
# =====================================================
ch_client = connect_clickhouse()
# =====================================================
# QUERY
# =====================================================
query = f"""
SELECT *
FROM dbo.[{TABLE_NAME}]
WHERE Project_Id = {PROJECT_ID}
"""
print("\nExecuting Query")
print(query)
# =====================================================
# RETRY SETTINGS
# =====================================================
retry_count = 0
max_retry = 5
# =====================================================
# MAIN RETRY LOOP
# =====================================================
while retry_count < max_retry:
try:
# =============================================
# READ SQL DATA
# =============================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
try:
print("\n================================")
print(
f"Processing Rows : "
f"{len(chunk)}"
)
print("================================")
# =====================================
# CLEAN DATA
# =====================================
chunk = clean_dataframe(chunk)
# =====================================
# DEBUG COLUMN TYPES
# =====================================
print("\nCOLUMN DATATYPES")
print(chunk.dtypes)
print("\nCOLUMN SAMPLE TYPES")
for col in chunk.columns:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
# =====================================
# TRUNCATE TABLE FIRST TIME ONLY
# =====================================
if (
TRUNCATE_BEFORE_LOAD
and
not table_truncated
):
print("\n================================")
print(
f"TRUNCATING TABLE : "
f"{TABLE_NAME}"
)
print("================================")
# IMPORTANT FIX
truncate_query = f"""
TRUNCATE TABLE
`{CH_CONFIG['database']}`.`{TABLE_NAME}`
"""
ch_client.command(
truncate_query
)
print(
"TABLE TRUNCATED SUCCESSFULLY"
)
table_truncated = True
# =====================================
# INSERT INTO CLICKHOUSE
# =====================================
print(
"\nINSERTING INTO CLICKHOUSE..."
)
ch_client.insert_df(
table=TABLE_NAME,
df=chunk,
database=CH_CONFIG['database']
)
print(
f"INSERTED : "
f"{len(chunk)} ROWS"
)
except Exception as insert_error:
print("\n================================")
print("INSERT FAILED")
print("================================")
print(str(insert_error))
traceback.print_exc()
# =================================
# SAVE ERROR LOG
# =================================
with open(
"insert_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : "
f"{datetime.now()}"
)
log.write(
f"\nTABLE : "
f"{TABLE_NAME}"
)
log.write(
f"\nERROR : "
f"{str(insert_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
# =============================================
# SUCCESS
# =============================================
break
# =================================================
# SQL CONNECTION FAILURE
# =================================================
except pyodbc.OperationalError as op_error:
retry_count += 1
print("\n================================")
print(
f"SQL CONNECTION LOST "
f"- RETRY {retry_count}"
)
print("================================")
print(str(op_error))
time.sleep(10)
try:
sql_conn.close()
except:
pass
# RECONNECT SQL
sql_conn = connect_sql()
# =================================================
# OTHER ERROR
# =================================================
except Exception as loop_error:
print("\n================================")
print("MAIN LOOP ERROR")
print("================================")
print(str(loop_error))
traceback.print_exc()
break
print("\n================================")
print("ETL COMPLETED SUCCESSFULLY")
print("================================")
# =========================================================
# MAIN ERROR
# =========================================================
except Exception as main_error:
print("\n================================")
print("MAIN ERROR")
print("================================")
print(str(main_error))
traceback.print_exc()
with open(
"main_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nERROR : {str(main_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
# =========================================================
# CLOSE CONNECTIONS
# =========================================================
finally:
try:
sql_conn.close()
print("\nSQL SERVER CONNECTION CLOSED")
except:
pass
try:
ch_client.close()
print("CLICKHOUSE CONNECTION CLOSED")
except:
pass
print("\n================================================")
print("ETL FINISHED :", datetime.now())
print("================================================")
PaidVisibility_Import.py
+545
View File
@@ -0,0 +1,545 @@
import pyodbc
import pandas as pd
import clickhouse_connect
import numpy as np
from datetime import datetime
import traceback
import warnings
# =========================================================
# IGNORE WARNINGS
# =========================================================
warnings.filterwarnings(
'ignore',
'pandas only supports SQLAlchemy connectable'
)
print("ETL Started :", datetime.now())
# =========================================================
# SQL SERVER CONNECTION
# =========================================================
SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};'
'SERVER=10.200.25.65;'
'DATABASE=CPMIndiaBusinessInsight;'
'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;'
)
# =========================================================
# CLICKHOUSE CONFIG
# =========================================================
CH_CONFIG = {
'host': '172.188.12.194',
'port': 8123,
'username': 'default',
'password': 'dipanshu_k',
'database': 'DaburIndia_BI'
}
# =========================================================
# TABLE NAME
# =========================================================
TABLE_NAME = 'PaidVisibility'
PROJECT_ID = 41654
# =========================================================
# LOAD SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CLICKHOUSE DATE COLUMNS
# =========================================================
DATE_COLUMNS = [
'visit_date'
]
# =========================================================
# CLICKHOUSE DATETIME COLUMNS
# =========================================================
DATETIME_COLUMNS = [
'create_date',
'update_date'
]
# =========================================================
# CLEAN DATAFRAME
# =========================================================
def clean_dataframe(df):
try:
# ---------------------------------------------
# Replace NaN
# ---------------------------------------------
df = df.replace({np.nan: None})
# ---------------------------------------------
# Process Column Wise
# ---------------------------------------------
for col in df.columns:
try:
print(f"\nCleaning Column : {col}")
# =====================================
# DATE32 COLUMNS
# =====================================
if col.lower() in [
x.lower() for x in DATE_COLUMNS
]:
print(f"Date32 Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
# Remove invalid dates
df[col] = df[col].where(
(df[col].dt.year >= 1970) &
(df[col].dt.year <= 2100)
)
# Convert to datetime.date
df[col] = df[col].apply(
lambda x:
x.date()
if pd.notnull(x)
else None
)
# =====================================
# DATETIME64 COLUMNS
# =====================================
elif col.lower() in [
x.lower() for x in DATETIME_COLUMNS
]:
print(f"DateTime Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
# Remove invalid dates
df[col] = df[col].where(
(df[col].dt.year >= 1970) &
(df[col].dt.year <= 2100)
)
# Convert to datetime.datetime
df[col] = df[col].apply(
lambda x:
x.to_pydatetime()
if pd.notnull(x)
else None
)
# =====================================
# INTEGER COLUMNS
# =====================================
elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
# =====================================
# FLOAT COLUMNS
# =====================================
elif pd.api.types.is_float_dtype(df[col]):
print(f"Float Column : {col}")
non_null = df[col].dropna()
# Convert whole float to int
if len(non_null) > 0 and (
(non_null % 1 == 0).all()
):
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
else:
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# =====================================
# OBJECT / STRING COLUMNS
# =====================================
else:
print(f"String/Object Column : {col}")
cleaned = []
for val in df[col]:
# NULL
if pd.isnull(val):
cleaned.append(None)
# INTEGER
elif isinstance(
val,
(
int,
np.integer
)
):
cleaned.append(int(val))
# FLOAT
elif isinstance(
val,
(
float,
np.floating
)
):
if np.isnan(val):
cleaned.append(None)
else:
if val.is_integer():
cleaned.append(int(val))
else:
cleaned.append(float(val))
# STRING
elif isinstance(val, str):
cleaned.append(val.strip())
# BOOLEAN
elif isinstance(val, bool):
cleaned.append(int(val))
# DATETIME
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# OTHER
else:
cleaned.append(str(val))
df[col] = cleaned
except Exception as col_error:
print("\n================================")
print(f"COLUMN FAILED : {col}")
print(str(col_error))
print("================================")
return df
except Exception as clean_error:
print("\n================================")
print("DATA CLEAN FAILED")
print(str(clean_error))
print("================================")
return df
# =========================================================
# MAIN PROCESS
# =========================================================
try:
# =====================================================
# CONNECT SQL SERVER
# =====================================================
sql_conn = pyodbc.connect(SQL_CONN_STR)
print("Connected to SQL Server")
# =====================================================
# CONNECT CLICKHOUSE
# =====================================================
ch_client = clickhouse_connect.get_client(**CH_CONFIG)
print("Connected to ClickHouse")
# =====================================================
# QUERY
# =====================================================
query = f"""
SELECT *
FROM dbo.[{TABLE_NAME}]
WHERE Project_Id = {PROJECT_ID}
"""
print("\nExecuting Query:")
print(query)
# =====================================================
# CHUNK SIZE
# =====================================================
chunk_size = 100000
total_rows = 0
# =====================================================
# READ DATA
# =====================================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
try:
print("\n================================")
print(f"Processing {len(chunk)} Rows")
print("================================")
# =================================================
# CLEAN DATA
# =================================================
chunk = clean_dataframe(chunk)
# =================================================
# DEBUG COLUMN TYPES
# =================================================
print("\nCOLUMN TYPES")
for col in chunk.columns:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
# =================================================
# DEBUG DATE COLUMN
# =================================================
if 'visit_date' in chunk.columns:
print("\nvisit_date Sample")
print(chunk['visit_date'].head())
sample = chunk['visit_date'].dropna()
if len(sample) > 0:
print(
"visit_date datatype:",
type(sample.iloc[0])
)
# =================================================
# TRUNCATE TABLE FIRST TIME ONLY
# =================================================
if TRUNCATE_BEFORE_LOAD and not table_truncated:
print("\n================================")
print(f"TRUNCATING TABLE : {TABLE_NAME}")
print("================================")
truncate_query = f"""
TRUNCATE TABLE
{CH_CONFIG['database']}.{TABLE_NAME}
"""
ch_client.command(truncate_query)
print("TABLE TRUNCATED SUCCESSFULLY")
table_truncated = True
# =================================================
# INSERT INTO CLICKHOUSE
# =================================================
print("\nInserting into ClickHouse...")
ch_client.insert_df(
table=TABLE_NAME,
df=chunk,
database=CH_CONFIG['database']
)
total_rows += len(chunk)
print(
f"\nInserted Total Rows : {total_rows}"
)
except Exception as chunk_error:
print("\n================================")
print("CHUNK INSERT FAILED")
print("================================")
print(str(chunk_error))
traceback.print_exc()
# =============================================
# SAVE ERROR LOG
# =============================================
with open(
"clickhouse_chunk_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nTABLE : {TABLE_NAME}"
)
log.write(
f"\nERROR : {str(chunk_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
print("\n================================")
print("ETL COMPLETED SUCCESSFULLY")
print(f"TOTAL ROWS INSERTED : {total_rows}")
print("================================")
# =========================================================
# MAIN ERROR
# =========================================================
except Exception as main_error:
print("\n================================")
print("MAIN ERROR")
print("================================")
print(str(main_error))
traceback.print_exc()
with open(
"clickhouse_main_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nERROR : {str(main_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
# =========================================================
# CLOSE CONNECTIONS
# =========================================================
finally:
try:
sql_conn.close()
print("\nSQL Server Connection Closed")
except:
pass
try:
ch_client.close()
print("ClickHouse Connection Closed")
except:
pass
print("\nETL Finished :", datetime.now())
SKU Master_Import.py
+632
View File
@@ -0,0 +1,632 @@
import pyodbc
import pandas as pd
import clickhouse_connect
import numpy as np
from datetime import datetime
import traceback
import warnings
# =========================================================
# IGNORE WARNINGS
# =========================================================
warnings.filterwarnings(
'ignore',
'pandas only supports SQLAlchemy connectable'
)
print("\n====================================")
print("ETL Started :", datetime.now())
print("====================================")
# =========================================================
# SQL SERVER CONNECTION
# =========================================================
SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};'
'SERVER=10.200.25.65;'
'DATABASE=CPMIndiaBusinessInsight;'
'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;'
)
# =========================================================
# CLICKHOUSE CONFIG
# =========================================================
CH_CONFIG = {
'host': '172.188.12.194',
'port': 8123,
'username': 'default',
'password': 'dipanshu_k',
'database': 'DaburIndia_BI'
}
# =========================================================
# TABLE DETAILS
# =========================================================
TABLE_NAME = 'SKU Master'
PROJECT_ID = 41654
# =========================================================
# SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CLICKHOUSE DATE COLUMNS
# =========================================================
DATE_COLUMNS = [
'visit_date'
]
# =========================================================
# CLICKHOUSE DATETIME COLUMNS
# =========================================================
DATETIME_COLUMNS = [
'create_date',
'update_date'
]
# =========================================================
# CLEAN DATAFRAME
# =========================================================
def clean_dataframe(df):
try:
# ---------------------------------------------
# Replace NaN with None
# ---------------------------------------------
df = df.replace({np.nan: None})
# ---------------------------------------------
# Process Each Column
# ---------------------------------------------
for col in df.columns:
try:
print(f"\nCleaning Column : {col}")
# =====================================
# DATE COLUMNS
# =====================================
if col.lower() in [
x.lower() for x in DATE_COLUMNS
]:
print(f"Date Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
cleaned_dates = []
for val in df[col]:
if pd.isnull(val):
cleaned_dates.append(None)
else:
cleaned_dates.append(
val.date()
)
df[col] = cleaned_dates
# =====================================
# DATETIME COLUMNS
# =====================================
elif col.lower() in [
x.lower() for x in DATETIME_COLUMNS
]:
print(f"DateTime Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
cleaned_datetime = []
for val in df[col]:
if pd.isnull(val):
cleaned_datetime.append(None)
else:
cleaned_datetime.append(
val.to_pydatetime()
)
df[col] = cleaned_datetime
# =====================================
# INTEGER COLUMNS
# =====================================
elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
# =====================================
# FLOAT COLUMNS
# =====================================
elif pd.api.types.is_float_dtype(df[col]):
print(f"Float Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
non_null = df[col].dropna()
# ---------------------------------
# Convert whole float to int
# Example:
# 12.0 -> 12
# ---------------------------------
if len(non_null) > 0 and (
(non_null % 1 == 0).all()
):
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
else:
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# =====================================
# OBJECT / STRING COLUMNS
# =====================================
else:
print(f"String/Object Column : {col}")
cleaned = []
for val in df[col]:
try:
# -------------------------
# NULL
# -------------------------
if pd.isnull(val):
cleaned.append(None)
# -------------------------
# STRING
# -------------------------
elif isinstance(val, str):
cleaned.append(
val.strip()
)
# -------------------------
# BOOLEAN
# -------------------------
elif isinstance(val, bool):
cleaned.append(
int(val)
)
# -------------------------
# INTEGER
# -------------------------
elif isinstance(
val,
(
int,
np.integer
)
):
cleaned.append(
int(val)
)
# -------------------------
# FLOAT
# -------------------------
elif isinstance(
val,
(
float,
np.floating
)
):
if np.isnan(val):
cleaned.append(None)
else:
if val.is_integer():
cleaned.append(
int(val)
)
else:
cleaned.append(
float(val)
)
# -------------------------
# DATETIME
# -------------------------
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# -------------------------
# DATE
# -------------------------
elif hasattr(val, 'year'):
cleaned.append(val)
# -------------------------
# OTHER
# -------------------------
else:
cleaned.append(
str(val)
)
except Exception as row_error:
print(
f"Row Cleaning Error "
f"in Column {col}"
)
print(str(row_error))
cleaned.append(None)
df[col] = cleaned
except Exception as col_error:
print("\n================================")
print(f"COLUMN FAILED : {col}")
print(str(col_error))
print("================================")
return df
except Exception as clean_error:
print("\n================================")
print("DATA CLEAN FAILED")
print(str(clean_error))
print(traceback.format_exc())
print("================================")
return df
# =========================================================
# MAIN PROCESS
# =========================================================
try:
# =====================================================
# CONNECT SQL SERVER
# =====================================================
print("\nConnecting SQL Server...")
sql_conn = pyodbc.connect(SQL_CONN_STR)
print("Connected to SQL Server")
# =====================================================
# CONNECT CLICKHOUSE
# =====================================================
print("\nConnecting ClickHouse...")
ch_client = clickhouse_connect.get_client(**CH_CONFIG)
print("Connected to ClickHouse")
# =====================================================
# QUERY
# =====================================================
query = f"""
SELECT *
FROM dbo.[{TABLE_NAME}]
WHERE Project_Id = {PROJECT_ID}
"""
print("\n====================================")
print("Executing Query")
print("====================================")
print(query)
# =====================================================
# CHUNK SIZE
# =====================================================
chunk_size = 100000
total_rows = 0
# =====================================================
# READ DATA
# =====================================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
try:
print("\n====================================")
print(f"Processing Rows : {len(chunk)}")
print("====================================")
# =================================================
# CLEAN DATA
# =================================================
chunk = clean_dataframe(chunk)
# =================================================
# DEBUG COLUMN TYPES
# =================================================
print("\nCOLUMN TYPES")
for col in chunk.columns:
try:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
except:
pass
# =================================================
# TRUNCATE TABLE
# =================================================
if TRUNCATE_BEFORE_LOAD and not table_truncated:
try:
print("\n====================================")
print(f"TRUNCATING : {TABLE_NAME}")
print("====================================")
truncate_query = f"""
TRUNCATE TABLE
`{CH_CONFIG['database']}`.`{TABLE_NAME}`
"""
print(truncate_query)
ch_client.command(
truncate_query
)
print(
"TABLE TRUNCATED SUCCESSFULLY"
)
table_truncated = True
except Exception as truncate_error:
print("\nTRUNCATE FAILED")
print(str(truncate_error))
raise
# =================================================
# INSERT DATA
# =================================================
try:
print("\n====================================")
print("INSERTING DATA INTO CLICKHOUSE")
print("====================================")
ch_client.insert_df(
table=f"`{TABLE_NAME}`",
df=chunk,
database=CH_CONFIG['database']
)
total_rows += len(chunk)
print(
f"\nTOTAL INSERTED : "
f"{total_rows}"
)
except Exception as insert_error:
print("\nINSERT FAILED")
print(str(insert_error))
traceback.print_exc()
# =============================================
# SAVE ERROR LOG
# =============================================
with open(
"clickhouse_insert_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nTABLE : {TABLE_NAME}"
)
log.write(
f"\nERROR : {str(insert_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
except Exception as chunk_error:
print("\n====================================")
print("CHUNK PROCESS FAILED")
print("====================================")
print(str(chunk_error))
traceback.print_exc()
continue
print("\n====================================")
print("ETL COMPLETED SUCCESSFULLY")
print(f"TOTAL ROWS INSERTED : {total_rows}")
print("====================================")
# =========================================================
# MAIN ERROR
# =========================================================
except Exception as main_error:
print("\n====================================")
print("MAIN ERROR")
print("====================================")
print(str(main_error))
traceback.print_exc()
with open(
"clickhouse_main_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nERROR : {str(main_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
# =========================================================
# CLOSE CONNECTIONS
# =========================================================
finally:
try:
sql_conn.close()
print("\nSQL Server Connection Closed")
except:
pass
try:
ch_client.close()
print("ClickHouse Connection Closed")
except:
pass
print("\n====================================")
print("ETL Finished :", datetime.now())
print("====================================")
Sales_Import.py
+604
View File
@@ -0,0 +1,604 @@
import pyodbc
import pandas as pd
import clickhouse_connect
import numpy as np
from datetime import datetime
import traceback
import warnings
import time
# =========================================================
# IGNORE WARNINGS
# =========================================================
warnings.filterwarnings(
'ignore',
'pandas only supports SQLAlchemy connectable'
)
print("\n================================================")
print("ETL STARTED :", datetime.now())
print("================================================")
# =========================================================
# SQL SERVER CONNECTION STRING
# =========================================================
SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};'
'SERVER=10.200.25.65;'
'DATABASE=CPMIndiaBusinessInsight;'
'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;'
'Connection Timeout=60;'
)
# =========================================================
# CLICKHOUSE CONFIG
# =========================================================
CH_CONFIG = {
'host': '172.188.12.194',
'port': 8123,
'username': 'default',
'password': 'dipanshu_k',
'database': 'DaburIndia_BI'
}
# =========================================================
# TABLE DETAILS
# =========================================================
TABLE_NAME = 'Sales'
PROJECT_ID = 41654
# =========================================================
# SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CHUNK SIZE
# =========================================================
chunk_size = 10000
# =========================================================
# CONNECT SQL SERVER
# =========================================================
def connect_sql():
try:
conn = pyodbc.connect(
SQL_CONN_STR,
autocommit=True
)
print("Connected SQL Server")
return conn
except Exception as e:
print("SQL CONNECTION FAILED")
print(str(e))
raise
# =========================================================
# CONNECT CLICKHOUSE
# =========================================================
def connect_clickhouse():
try:
client = clickhouse_connect.get_client(
**CH_CONFIG
)
print("Connected ClickHouse")
return client
except Exception as e:
print("CLICKHOUSE CONNECTION FAILED")
print(str(e))
raise
# =========================================================
# CLEAN DATAFRAME
# =========================================================
def clean_dataframe(df):
try:
# ---------------------------------------------
# Replace NaN
# ---------------------------------------------
df = df.replace({np.nan: None})
# ---------------------------------------------
# Process Column Wise
# ---------------------------------------------
for col in df.columns:
try:
print(f"\nCleaning Column : {col}")
# =====================================
# AUTO DETECT DATE / TIME COLUMNS
# =====================================
if (
'date' in col.lower()
or 'time' in col.lower()
):
print(f"Date Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
cleaned_dates = []
for val in df[col]:
if pd.isnull(val):
cleaned_dates.append(None)
else:
cleaned_dates.append(
val.to_pydatetime()
)
df[col] = cleaned_dates
# =====================================
# INTEGER COLUMNS
# =====================================
elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
# =====================================
# FLOAT COLUMNS
# =====================================
elif pd.api.types.is_float_dtype(df[col]):
print(f"Float Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# =====================================
# OBJECT / STRING COLUMNS
# =====================================
else:
print(f"String/Object Column : {col}")
cleaned = []
for val in df[col]:
# NULL
if pd.isnull(val):
cleaned.append(None)
# DATETIME
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# INTEGER
elif isinstance(
val,
(
int,
np.integer
)
):
cleaned.append(
int(val)
)
# FLOAT
elif isinstance(
val,
(
float,
np.floating
)
):
if np.isnan(val):
cleaned.append(None)
else:
cleaned.append(
float(val)
)
# BOOLEAN
elif isinstance(
val,
bool
):
cleaned.append(
int(val)
)
# STRING
else:
cleaned.append(
str(val).strip()
)
df[col] = cleaned
except Exception as col_error:
print("\n================================")
print(f"COLUMN FAILED : {col}")
print(str(col_error))
print("================================")
return df
except Exception as clean_error:
print("\n================================")
print("DATA CLEAN FAILED")
print(str(clean_error))
print("================================")
return df
# =========================================================
# MAIN PROCESS
# =========================================================
try:
# =====================================================
# CONNECT SQL SERVER
# =====================================================
sql_conn = connect_sql()
# =====================================================
# CONNECT CLICKHOUSE
# =====================================================
ch_client = connect_clickhouse()
# =====================================================
# QUERY
# =====================================================
query = f"""
SELECT *
FROM dbo.[{TABLE_NAME}]
WHERE Project_Id = {PROJECT_ID}
"""
print("\nExecuting Query")
print(query)
# =====================================================
# RETRY SETTINGS
# =====================================================
retry_count = 0
max_retry = 5
# =====================================================
# MAIN RETRY LOOP
# =====================================================
while retry_count < max_retry:
try:
# =============================================
# READ SQL DATA
# =============================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
try:
print("\n================================")
print(
f"Processing Rows : "
f"{len(chunk)}"
)
print("================================")
# =====================================
# CLEAN DATA
# =====================================
chunk = clean_dataframe(chunk)
# =====================================
# DEBUG COLUMN TYPES
# =====================================
print("\nCOLUMN DATATYPES")
print(chunk.dtypes)
print("\nCOLUMN SAMPLE TYPES")
for col in chunk.columns:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
# =====================================
# TRUNCATE TABLE FIRST TIME ONLY
# =====================================
if (
TRUNCATE_BEFORE_LOAD
and
not table_truncated
):
print("\n================================")
print(
f"TRUNCATING TABLE : "
f"{TABLE_NAME}"
)
print("================================")
# IMPORTANT FIX
truncate_query = f"""
TRUNCATE TABLE
`{CH_CONFIG['database']}`.`{TABLE_NAME}`
"""
ch_client.command(
truncate_query
)
print(
"TABLE TRUNCATED SUCCESSFULLY"
)
table_truncated = True
# =====================================
# INSERT INTO CLICKHOUSE
# =====================================
print(
"\nINSERTING INTO CLICKHOUSE..."
)
ch_client.insert_df(
table=TABLE_NAME,
df=chunk,
database=CH_CONFIG['database']
)
print(
f"INSERTED : "
f"{len(chunk)} ROWS"
)
except Exception as insert_error:
print("\n================================")
print("INSERT FAILED")
print("================================")
print(str(insert_error))
traceback.print_exc()
# =================================
# SAVE ERROR LOG
# =================================
with open(
"insert_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : "
f"{datetime.now()}"
)
log.write(
f"\nTABLE : "
f"{TABLE_NAME}"
)
log.write(
f"\nERROR : "
f"{str(insert_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
# =============================================
# SUCCESS
# =============================================
break
# =================================================
# SQL CONNECTION FAILURE
# =================================================
except pyodbc.OperationalError as op_error:
retry_count += 1
print("\n================================")
print(
f"SQL CONNECTION LOST "
f"- RETRY {retry_count}"
)
print("================================")
print(str(op_error))
time.sleep(10)
try:
sql_conn.close()
except:
pass
# RECONNECT SQL
sql_conn = connect_sql()
# =================================================
# OTHER ERROR
# =================================================
except Exception as loop_error:
print("\n================================")
print("MAIN LOOP ERROR")
print("================================")
print(str(loop_error))
traceback.print_exc()
break
print("\n================================")
print("ETL COMPLETED SUCCESSFULLY")
print("================================")
# =========================================================
# MAIN ERROR
# =========================================================
except Exception as main_error:
print("\n================================")
print("MAIN ERROR")
print("================================")
print(str(main_error))
traceback.print_exc()
with open(
"main_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nERROR : {str(main_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
# =========================================================
# CLOSE CONNECTIONS
# =========================================================
finally:
try:
sql_conn.close()
print("\nSQL SERVER CONNECTION CLOSED")
except:
pass
try:
ch_client.close()
print("CLICKHOUSE CONNECTION CLOSED")
except:
pass
print("\n================================================")
print("ETL FINISHED :", datetime.now())
print("================================================")
[Web Logins]_Import.py
+632
View File
@@ -0,0 +1,632 @@
import pyodbc
import pandas as pd
import clickhouse_connect
import numpy as np
from datetime import datetime
import traceback
import warnings
# =========================================================
# IGNORE WARNINGS
# =========================================================
warnings.filterwarnings(
'ignore',
'pandas only supports SQLAlchemy connectable'
)
print("\n====================================")
print("ETL Started :", datetime.now())
print("====================================")
# =========================================================
# SQL SERVER CONNECTION
# =========================================================
SQL_CONN_STR = (
'DRIVER={ODBC Driver 17 for SQL Server};'
'SERVER=10.200.25.65;'
'DATABASE=CPMIndiaBusinessInsight;'
'UID=bsgteam_test;'
'PWD=B$gt3@m#00512;'
'TrustServerCertificate=yes;'
)
# =========================================================
# CLICKHOUSE CONFIG
# =========================================================
CH_CONFIG = {
'host': '172.188.12.194',
'port': 8123,
'username': 'default',
'password': 'dipanshu_k',
'database': 'DaburIndia_BI'
}
# =========================================================
# TABLE DETAILS
# =========================================================
TABLE_NAME = 'Web Logins'
PROJECT_ID = 41654
# =========================================================
# SETTINGS
# =========================================================
TRUNCATE_BEFORE_LOAD = True
table_truncated = False
# =========================================================
# CLICKHOUSE DATE COLUMNS
# =========================================================
DATE_COLUMNS = [
'visit_date'
]
# =========================================================
# CLICKHOUSE DATETIME COLUMNS
# =========================================================
DATETIME_COLUMNS = [
'create_date',
'update_date'
]
# =========================================================
# CLEAN DATAFRAME
# =========================================================
def clean_dataframe(df):
try:
# ---------------------------------------------
# Replace NaN with None
# ---------------------------------------------
df = df.replace({np.nan: None})
# ---------------------------------------------
# Process Each Column
# ---------------------------------------------
for col in df.columns:
try:
print(f"\nCleaning Column : {col}")
# =====================================
# DATE COLUMNS
# =====================================
if col.lower() in [
x.lower() for x in DATE_COLUMNS
]:
print(f"Date Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
cleaned_dates = []
for val in df[col]:
if pd.isnull(val):
cleaned_dates.append(None)
else:
cleaned_dates.append(
val.date()
)
df[col] = cleaned_dates
# =====================================
# DATETIME COLUMNS
# =====================================
elif col.lower() in [
x.lower() for x in DATETIME_COLUMNS
]:
print(f"DateTime Column : {col}")
df[col] = pd.to_datetime(
df[col],
errors='coerce'
)
cleaned_datetime = []
for val in df[col]:
if pd.isnull(val):
cleaned_datetime.append(None)
else:
cleaned_datetime.append(
val.to_pydatetime()
)
df[col] = cleaned_datetime
# =====================================
# INTEGER COLUMNS
# =====================================
elif pd.api.types.is_integer_dtype(df[col]):
print(f"Integer Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
# =====================================
# FLOAT COLUMNS
# =====================================
elif pd.api.types.is_float_dtype(df[col]):
print(f"Float Column : {col}")
df[col] = pd.to_numeric(
df[col],
errors='coerce'
)
non_null = df[col].dropna()
# ---------------------------------
# Convert whole float to int
# Example:
# 12.0 -> 12
# ---------------------------------
if len(non_null) > 0 and (
(non_null % 1 == 0).all()
):
df[col] = df[col].apply(
lambda x:
int(x)
if pd.notnull(x)
else None
)
else:
df[col] = df[col].apply(
lambda x:
float(x)
if pd.notnull(x)
else None
)
# =====================================
# OBJECT / STRING COLUMNS
# =====================================
else:
print(f"String/Object Column : {col}")
cleaned = []
for val in df[col]:
try:
# -------------------------
# NULL
# -------------------------
if pd.isnull(val):
cleaned.append(None)
# -------------------------
# STRING
# -------------------------
elif isinstance(val, str):
cleaned.append(
val.strip()
)
# -------------------------
# BOOLEAN
# -------------------------
elif isinstance(val, bool):
cleaned.append(
int(val)
)
# -------------------------
# INTEGER
# -------------------------
elif isinstance(
val,
(
int,
np.integer
)
):
cleaned.append(
int(val)
)
# -------------------------
# FLOAT
# -------------------------
elif isinstance(
val,
(
float,
np.floating
)
):
if np.isnan(val):
cleaned.append(None)
else:
if val.is_integer():
cleaned.append(
int(val)
)
else:
cleaned.append(
float(val)
)
# -------------------------
# DATETIME
# -------------------------
elif isinstance(
val,
(
datetime,
pd.Timestamp
)
):
if isinstance(
val,
pd.Timestamp
):
cleaned.append(
val.to_pydatetime()
)
else:
cleaned.append(val)
# -------------------------
# DATE
# -------------------------
elif hasattr(val, 'year'):
cleaned.append(val)
# -------------------------
# OTHER
# -------------------------
else:
cleaned.append(
str(val)
)
except Exception as row_error:
print(
f"Row Cleaning Error "
f"in Column {col}"
)
print(str(row_error))
cleaned.append(None)
df[col] = cleaned
except Exception as col_error:
print("\n================================")
print(f"COLUMN FAILED : {col}")
print(str(col_error))
print("================================")
return df
except Exception as clean_error:
print("\n================================")
print("DATA CLEAN FAILED")
print(str(clean_error))
print(traceback.format_exc())
print("================================")
return df
# =========================================================
# MAIN PROCESS
# =========================================================
try:
# =====================================================
# CONNECT SQL SERVER
# =====================================================
print("\nConnecting SQL Server...")
sql_conn = pyodbc.connect(SQL_CONN_STR)
print("Connected to SQL Server")
# =====================================================
# CONNECT CLICKHOUSE
# =====================================================
print("\nConnecting ClickHouse...")
ch_client = clickhouse_connect.get_client(**CH_CONFIG)
print("Connected to ClickHouse")
# =====================================================
# QUERY
# =====================================================
query = f"""
SELECT *
FROM dbo.[{TABLE_NAME}]
WHERE Project_Id = {PROJECT_ID}
"""
print("\n====================================")
print("Executing Query")
print("====================================")
print(query)
# =====================================================
# CHUNK SIZE
# =====================================================
chunk_size = 100000
total_rows = 0
# =====================================================
# READ DATA
# =====================================================
for chunk in pd.read_sql(
query,
sql_conn,
chunksize=chunk_size
):
try:
print("\n====================================")
print(f"Processing Rows : {len(chunk)}")
print("====================================")
# =================================================
# CLEAN DATA
# =================================================
chunk = clean_dataframe(chunk)
# =================================================
# DEBUG COLUMN TYPES
# =================================================
print("\nCOLUMN TYPES")
for col in chunk.columns:
try:
sample = chunk[col].dropna()
if len(sample) > 0:
print(
col,
type(sample.iloc[0]),
sample.iloc[0]
)
except:
pass
# =================================================
# TRUNCATE TABLE
# =================================================
if TRUNCATE_BEFORE_LOAD and not table_truncated:
try:
print("\n====================================")
print(f"TRUNCATING : {TABLE_NAME}")
print("====================================")
truncate_query = f"""
TRUNCATE TABLE
`{CH_CONFIG['database']}`.`{TABLE_NAME}`
"""
print(truncate_query)
ch_client.command(
truncate_query
)
print(
"TABLE TRUNCATED SUCCESSFULLY"
)
table_truncated = True
except Exception as truncate_error:
print("\nTRUNCATE FAILED")
print(str(truncate_error))
raise
# =================================================
# INSERT DATA
# =================================================
try:
print("\n====================================")
print("INSERTING DATA INTO CLICKHOUSE")
print("====================================")
ch_client.insert_df(
table=f"`{TABLE_NAME}`",
df=chunk,
database=CH_CONFIG['database']
)
total_rows += len(chunk)
print(
f"\nTOTAL INSERTED : "
f"{total_rows}"
)
except Exception as insert_error:
print("\nINSERT FAILED")
print(str(insert_error))
traceback.print_exc()
# =============================================
# SAVE ERROR LOG
# =============================================
with open(
"clickhouse_insert_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nTABLE : {TABLE_NAME}"
)
log.write(
f"\nERROR : {str(insert_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
continue
except Exception as chunk_error:
print("\n====================================")
print("CHUNK PROCESS FAILED")
print("====================================")
print(str(chunk_error))
traceback.print_exc()
continue
print("\n====================================")
print("ETL COMPLETED SUCCESSFULLY")
print(f"TOTAL ROWS INSERTED : {total_rows}")
print("====================================")
# =========================================================
# MAIN ERROR
# =========================================================
except Exception as main_error:
print("\n====================================")
print("MAIN ERROR")
print("====================================")
print(str(main_error))
traceback.print_exc()
with open(
"clickhouse_main_error.log",
"a",
encoding="utf-8"
) as log:
log.write(
"\n\n================================"
)
log.write(
f"\nTIME : {datetime.now()}"
)
log.write(
f"\nERROR : {str(main_error)}"
)
log.write(
f"\nTRACEBACK :\n"
f"{traceback.format_exc()}"
)
log.write(
"\n================================"
)
# =========================================================
# CLOSE CONNECTIONS
# =========================================================
finally:
try:
sql_conn.close()
print("\nSQL Server Connection Closed")
except:
pass
try:
ch_client.close()
print("ClickHouse Connection Closed")
except:
pass
print("\n====================================")
print("ETL Finished :", datetime.now())
print("====================================")
clickhouse_chunk_error.log
+8314
View File
File diff suppressed because it is too large Load Diff
clickhouse_insert_error.log
+231
View File
@@ -0,0 +1,231 @@
================================
TIME : 2026-05-19 17:13:53.695971
TABLE : Sales
ERROR : Error ('Connection aborted.', TimeoutError('timed out')) executing HTTP request attempt 1 (http://172.188.12.194:8123)
TRACEBACK :
Traceback (most recent call last):
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 788, in urlopen
response = self._make_request(
conn,
...<10 lines>...
**response_kw,
)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 493, in _make_request
conn.request(
~~~~~~~~~~~~^
method,
^^^^^^^
...<6 lines>...
enforce_content_length=enforce_content_length,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connection.py", line 512, in request
self.send(b"%x\r\n%b\r\n" % (len(chunk), chunk))
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\http\client.py", line 1086, in send
self.sock.sendall(data)
~~~~~~~~~~~~~~~~~^^^^^^
TimeoutError: timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\httpclient.py", line 546, in _raw_request
response = self.http.request(method, url, **kwargs)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\_request_methods.py", line 143, in request
return self.request_encode_body(
~~~~~~~~~~~~~~~~~~~~~~~~^
method, url, fields=fields, headers=headers, **urlopen_kw
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\_request_methods.py", line 278, in request_encode_body
return self.urlopen(method, url, **extra_kw)
~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\poolmanager.py", line 457, in urlopen
response = conn.urlopen(method, u.request_uri, **kw)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 842, in urlopen
retries = retries.increment(
method, url, error=new_e, _pool=self, _stacktrace=sys.exc_info()[2]
)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\util\retry.py", line 498, in increment
raise reraise(type(error), error, _stacktrace)
~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\util\util.py", line 38, in reraise
raise value.with_traceback(tb)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 788, in urlopen
response = self._make_request(
conn,
...<10 lines>...
**response_kw,
)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 493, in _make_request
conn.request(
~~~~~~~~~~~~^
method,
^^^^^^^
...<6 lines>...
enforce_content_length=enforce_content_length,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connection.py", line 512, in request
self.send(b"%x\r\n%b\r\n" % (len(chunk), chunk))
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\http\client.py", line 1086, in send
self.sock.sendall(data)
~~~~~~~~~~~~~~~~~^^^^^^
urllib3.exceptions.ProtocolError: ('Connection aborted.', TimeoutError('timed out'))
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "d:\Python Code\Sales_Import.py", line 494, in <module>
ch_client.insert_df(
~~~~~~~~~~~~~~~~~~~^
table=f"`{TABLE_NAME}`",
^^^^^^^^^^^^^^^^^^^^^^^^
df=chunk,
^^^^^^^^^
database=CH_CONFIG['database']
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\client.py", line 1013, in insert_df
return self.insert(table,
~~~~~~~~~~~^^^^^^^
df,
^^^
...<5 lines>...
transport_settings=transport_settings,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
context=context)
^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\client.py", line 978, in insert
return self.data_insert(context)
~~~~~~~~~~~~~~~~^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\httpclient.py", line 347, in data_insert
response = self._raw_request(block_gen, params, headers, error_handler=error_handler, server_wait=False)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\httpclient.py", line 558, in _raw_request
raise OperationalError(f'Error {ex} executing HTTP request attempt {attempts}{err_url}') from ex
clickhouse_connect.driver.exceptions.OperationalError: Error ('Connection aborted.', TimeoutError('timed out')) executing HTTP request attempt 1 (http://172.188.12.194:8123)
================================
================================
TIME : 2026-05-19 17:15:26.425862
TABLE : Sales
ERROR : Error ('Connection aborted.', TimeoutError('timed out')) executing HTTP request attempt 1 (http://172.188.12.194:8123)
TRACEBACK :
Traceback (most recent call last):
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 788, in urlopen
response = self._make_request(
conn,
...<10 lines>...
**response_kw,
)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 493, in _make_request
conn.request(
~~~~~~~~~~~~^
method,
^^^^^^^
...<6 lines>...
enforce_content_length=enforce_content_length,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connection.py", line 512, in request
self.send(b"%x\r\n%b\r\n" % (len(chunk), chunk))
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\http\client.py", line 1086, in send
self.sock.sendall(data)
~~~~~~~~~~~~~~~~~^^^^^^
TimeoutError: timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\httpclient.py", line 546, in _raw_request
response = self.http.request(method, url, **kwargs)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\_request_methods.py", line 143, in request
return self.request_encode_body(
~~~~~~~~~~~~~~~~~~~~~~~~^
method, url, fields=fields, headers=headers, **urlopen_kw
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\_request_methods.py", line 278, in request_encode_body
return self.urlopen(method, url, **extra_kw)
~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\poolmanager.py", line 457, in urlopen
response = conn.urlopen(method, u.request_uri, **kw)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 842, in urlopen
retries = retries.increment(
method, url, error=new_e, _pool=self, _stacktrace=sys.exc_info()[2]
)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\util\retry.py", line 498, in increment
raise reraise(type(error), error, _stacktrace)
~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\util\util.py", line 38, in reraise
raise value.with_traceback(tb)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 788, in urlopen
response = self._make_request(
conn,
...<10 lines>...
**response_kw,
)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connectionpool.py", line 493, in _make_request
conn.request(
~~~~~~~~~~~~^
method,
^^^^^^^
...<6 lines>...
enforce_content_length=enforce_content_length,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\urllib3\connection.py", line 512, in request
self.send(b"%x\r\n%b\r\n" % (len(chunk), chunk))
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\http\client.py", line 1086, in send
self.sock.sendall(data)
~~~~~~~~~~~~~~~~~^^^^^^
urllib3.exceptions.ProtocolError: ('Connection aborted.', TimeoutError('timed out'))
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "d:\Python Code\Sales_Import.py", line 494, in <module>
ch_client.insert_df(
~~~~~~~~~~~~~~~~~~~^
table=f"`{TABLE_NAME}`",
^^^^^^^^^^^^^^^^^^^^^^^^
df=chunk,
^^^^^^^^^
database=CH_CONFIG['database']
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\client.py", line 1013, in insert_df
return self.insert(table,
~~~~~~~~~~~^^^^^^^
df,
^^^
...<5 lines>...
transport_settings=transport_settings,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
context=context)
^^^^^^^^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\client.py", line 978, in insert
return self.data_insert(context)
~~~~~~~~~~~~~~~~^^^^^^^^^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\httpclient.py", line 347, in data_insert
response = self._raw_request(block_gen, params, headers, error_handler=error_handler, server_wait=False)
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\clickhouse_connect\driver\httpclient.py", line 558, in _raw_request
raise OperationalError(f'Error {ex} executing HTTP request attempt {attempts}{err_url}') from ex
clickhouse_connect.driver.exceptions.OperationalError: Error ('Connection aborted.', TimeoutError('timed out')) executing HTTP request attempt 1 (http://172.188.12.194:8123)
================================
clickhouse_main_error.log
+99
View File
@@ -89,4 +89,103 @@ Traceback (most recent call last):
^^^^^^^^^^ ^^^^^^^^^^
NameError: name 'PROJECT_ID' is not defined. Did you mean: 'PROJECTID'? NameError: name 'PROJECT_ID' is not defined. Did you mean: 'PROJECTID'?
================================
================================
TIME : 2026-05-19 15:19:40.194819
ERROR : ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: An existing connection was forcibly closed by the remote host.\r\n (10054) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10054)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Import.py", line 345, in <module>
for chunk in pd.read_sql(
~~~~~~~~~~~^
query,
^^^^^^
sql_conn,
^^^^^^^^^
chunksize=chunk_size
^^^^^^^^^^^^^^^^^^^^
):
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\pandas\io\sql.py", line 2730, in _query_iterator
data = cursor.fetchmany(chunksize)
pyodbc.OperationalError: ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: An existing connection was forcibly closed by the remote host.\r\n (10054) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10054)')
================================
================================
TIME : 2026-05-19 15:26:07.910371
ERROR : ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [5]. (5) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (5)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\OQaD Import.py", line 310, in <module>
sql_conn = pyodbc.connect(SQL_CONN_STR)
pyodbc.OperationalError: ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [5]. (5) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (5)')
================================
================================
TIME : 2026-05-19 16:01:03.630328
ERROR : ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.\r\n (10060) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10060)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Import.py", line 343, in <module>
for chunk in pd.read_sql(
~~~~~~~~~~~^
query,
^^^^^^
sql_conn,
^^^^^^^^^
chunksize=chunk_size
^^^^^^^^^^^^^^^^^^^^
):
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\pandas\io\sql.py", line 2730, in _query_iterator
data = cursor.fetchmany(chunksize)
pyodbc.OperationalError: ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.\r\n (10060) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10060)')
================================
================================
TIME : 2026-05-19 16:36:09.557213
ERROR : ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.\r\n (10060) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10060)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 371, in <module>
for chunk in pd.read_sql(
~~~~~~~~~~~^
query,
^^^^^^
sql_conn,
^^^^^^^^^
chunksize=chunk_size
^^^^^^^^^^^^^^^^^^^^
):
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\pandas\io\sql.py", line 2730, in _query_iterator
data = cursor.fetchmany(chunksize)
pyodbc.OperationalError: ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.\r\n (10060) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10060)')
================================
================================
TIME : 2026-05-19 17:16:08.366780
ERROR : ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: An existing connection was forcibly closed by the remote host.\r\n (10054) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10054)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\Sales_Import.py", line 411, in <module>
for chunk in pd.read_sql(
~~~~~~~~~~~^
query,
^^^^^^
sql_conn,
^^^^^^^^^
chunksize=chunk_size
^^^^^^^^^^^^^^^^^^^^
):
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\pandas\io\sql.py", line 2730, in _query_iterator
data = cursor.fetchmany(chunksize)
pyodbc.OperationalError: ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: An existing connection was forcibly closed by the remote host.\r\n (10054) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10054)')
================================ ================================
insert_error.log
+13248
View File
File diff suppressed because it is too large Load Diff
main_error.log
+85
View File
@@ -0,0 +1,85 @@
================================
TIME : 2026-05-20 09:30:27.532149
ERROR : ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [2]. (2) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (2)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 313, in <module>
sql_conn = connect_sql()
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 70, in connect_sql
conn = pyodbc.connect(
SQL_CONN_STR,
autocommit=True
)
pyodbc.OperationalError: ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [2]. (2) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (2)')
================================
================================
TIME : 2026-05-20 10:38:12.600484
ERROR : ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [64]. (64) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (64)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 348, in <module>
for chunk in pd.read_sql(
~~~~~~~~~~~^
query,
^^^^^^
sql_conn,
^^^^^^^^^
chunksize=chunk_size
^^^^^^^^^^^^^^^^^^^^
):
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\pandas\io\sql.py", line 2730, in _query_iterator
data = cursor.fetchmany(chunksize)
pyodbc.OperationalError: ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: An existing connection was forcibly closed by the remote host.\r\n (10054) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10054)')
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 518, in <module>
sql_conn = connect_sql()
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 70, in connect_sql
conn = pyodbc.connect(
SQL_CONN_STR,
autocommit=True
)
pyodbc.OperationalError: ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [64]. (64) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (64)')
================================
================================
TIME : 2026-05-20 12:28:25.483277
ERROR : ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [53]. (53) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (53)')
TRACEBACK :
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 348, in <module>
for chunk in pd.read_sql(
~~~~~~~~~~~^
query,
^^^^^^
sql_conn,
^^^^^^^^^
chunksize=chunk_size
^^^^^^^^^^^^^^^^^^^^
):
^
File "C:\Users\dipanshuk\AppData\Local\Python\pythoncore-3.14-64\Lib\site-packages\pandas\io\sql.py", line 2730, in _query_iterator
data = cursor.fetchmany(chunksize)
pyodbc.OperationalError: ('08S01', '[08S01] [Microsoft][ODBC Driver 17 for SQL Server]TCP Provider: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.\r\n (10060) (SQLGetData); [08S01] [Microsoft][ODBC Driver 17 for SQL Server]Communication link failure (10060)')
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 518, in <module>
sql_conn = connect_sql()
File "d:\Python Code\PaidVisibility_Compliance Import.py", line 70, in connect_sql
conn = pyodbc.connect(
SQL_CONN_STR,
autocommit=True
)
pyodbc.OperationalError: ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]Named Pipes Provider: Could not open a connection to SQL Server [53]. (53) (SQLDriverConnect); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Login timeout expired (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [08001] [Microsoft][ODBC Driver 17 for SQL Server]A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online. (53)')
================================