54 lines
1.8 KiB
Python
54 lines
1.8 KiB
Python
import os
|
|
import pandas as pd
|
|
from sqlalchemy import create_engine
|
|
from dotenv import load_dotenv
|
|
|
|
# Load environment variables from .env file
|
|
load_dotenv()
|
|
|
|
# Get DB connection parameters from environment
|
|
DB_USER = os.getenv('DB_USER')
|
|
DB_PASSWORD = os.getenv('DB_PASSWORD')
|
|
DB_HOST = os.getenv('DB_HOST')
|
|
DB_PORT = os.getenv('DB_PORT')
|
|
DB_NAME = os.getenv('DB_NAME')
|
|
|
|
# Create a connection string
|
|
connection_string = f"mariadb+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}"
|
|
|
|
# Create the SQLAlchemy engine
|
|
engine = create_engine(connection_string)
|
|
|
|
# Define a list of file paths and corresponding table names
|
|
file_paths = [
|
|
('sec_data/2024q1/num.txt', 'num'),
|
|
('sec_data/2024q1/pre.txt', 'pre'),
|
|
('sec_data/2024q1/sub.txt', 'sub'),
|
|
('sec_data/2024q1/tag.txt', 'tag')
|
|
]
|
|
|
|
# Loop through each file and write the data to the database
|
|
for i, (file_path, table_name) in enumerate(file_paths):
|
|
print(f"\nAnalyzing {file_path} (File {i+1}/4)...")
|
|
|
|
# Read the data into a Pandas DataFrame
|
|
df = pd.read_csv(file_path, sep='\t')
|
|
|
|
# Inspect the DataFrame
|
|
print("First rows of the DataFrame:")
|
|
print(df.head(10))
|
|
|
|
# Get the DataFrame Information
|
|
print("\nSummary Information:")
|
|
print(df.info())
|
|
|
|
# Check if there are any missing values in the DataFrame
|
|
missing_values = df.isnull().sum()
|
|
print("\nMissing Values:")
|
|
print(missing_values)
|
|
|
|
# Write the DataFrame to the corresponding table in the MariaDB database
|
|
df.to_sql(table_name, con=engine, if_exists='replace', index=False)
|
|
print(f"\nData from {file_path} written to the '{table_name}' table in the database.")
|
|
|
|
print("\nAll files have been processed and written to the database.") |