| import pandas as pd
|
| import json
|
| import os
|
|
|
| DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'data')
|
|
|
| def load_sales_data():
|
| path = os.path.join(DATA_DIR, 'sales_data.csv')
|
| if not os.path.exists(path):
|
| raise FileNotFoundError(f"{path} not found.")
|
| df = pd.read_csv(path)
|
| df['Date'] = pd.to_datetime(df['Date'])
|
| return df
|
|
|
| def load_web_logs():
|
| path = os.path.join(DATA_DIR, 'web_logs.json')
|
| if not os.path.exists(path):
|
| raise FileNotFoundError(f"{path} not found.")
|
| with open(path, 'r') as f:
|
| data = json.load(f)
|
| df = pd.DataFrame(data)
|
| df['timestamp'] = pd.to_datetime(df['timestamp'])
|
| return df
|
|
|
| def load_reviews():
|
| path = os.path.join(DATA_DIR, 'customer_reviews.csv')
|
| if not os.path.exists(path):
|
| raise FileNotFoundError(f"{path} not found.")
|
| df = pd.read_csv(path)
|
| df['Date'] = pd.to_datetime(df['Date'])
|
| return df
|
|
|
| def get_integrated_data():
|
| """
|
| Simulates integration by merging Sales and Reviews on Product?
|
| Or mostly just providing a unified access point.
|
| Returns a dictionary of dataframes.
|
| """
|
| sales = load_sales_data()
|
| logs = load_web_logs()
|
| reviews = load_reviews()
|
|
|
| return {
|
| 'sales': sales,
|
| 'logs': logs,
|
| 'reviews': reviews
|
| }
|
|
|
| def clean_sales_data(df):
|
|
|
| df = df[(df['Quantity'] > 0) & (df['UnitPrice'] > 0)]
|
| return df
|
|
|
