| import pandas as pd
|
| import numpy as np
|
| from sklearn.cluster import KMeans
|
| from sklearn.preprocessing import StandardScaler
|
| from textblob import TextBlob
|
| from sklearn.linear_model import LinearRegression
|
|
|
| def perform_customer_segmentation(sales_df, n_clusters=4):
|
| """
|
| RFM (Recency, Frequency, Monetary) Clustering
|
| """
|
|
|
| current_date = sales_df['Date'].max()
|
|
|
| rfm = sales_df.groupby('CustomerID').agg({
|
| 'Date': lambda x: (current_date - x.max()).days,
|
| 'TransactionID': 'count',
|
| 'TotalPrice': 'sum'
|
| }).rename(columns={
|
| 'Date': 'Recency',
|
| 'TransactionID': 'Frequency',
|
| 'TotalPrice': 'Monetary'
|
| })
|
|
|
|
|
| scaler = StandardScaler()
|
| rfm_scaled = scaler.fit_transform(rfm)
|
|
|
|
|
| kmeans = KMeans(n_clusters=n_clusters, random_state=42, n_init=10)
|
| rfm['Cluster'] = kmeans.fit_predict(rfm_scaled)
|
|
|
|
|
|
|
| return rfm
|
|
|
| def forecast_sales(sales_df, days_to_forecast=30):
|
| """
|
| Simple Linear Regression on daily sales
|
| """
|
| daily_sales = sales_df.set_index('Date').resample('D')['TotalPrice'].sum().reset_index()
|
| daily_sales['DayIndex'] = np.arange(len(daily_sales))
|
|
|
| X = daily_sales[['DayIndex']]
|
| y = daily_sales['TotalPrice']
|
|
|
| model = LinearRegression()
|
| model.fit(X, y)
|
|
|
|
|
| first_future_idx = int(daily_sales['DayIndex'].max()) + 1
|
| future_indices = np.arange(first_future_idx, first_future_idx + days_to_forecast).reshape(-1, 1)
|
| future_df = pd.DataFrame(future_indices, columns=['DayIndex'])
|
| predictions = model.predict(future_df)
|
|
|
| last_date = daily_sales['Date'].max()
|
| future_dates = [last_date + pd.Timedelta(days=i) for i in range(1, days_to_forecast + 1)]
|
|
|
| forecast_df = pd.DataFrame({
|
| 'Date': future_dates,
|
| 'Predicted_Sales': predictions
|
| })
|
|
|
| return daily_sales, forecast_df
|
|
|
| def analyze_sentiment(reviews_df):
|
| """
|
| Apply TextBlob to get polarity
|
| """
|
| def get_polarity(text):
|
| return TextBlob(str(text)).sentiment.polarity
|
|
|
| reviews_df['Sentiment_Score'] = reviews_df['ReviewText'].apply(get_polarity)
|
|
|
|
|
| def label_sentiment(score):
|
| if score > 0.1: return 'Positive'
|
| if score < -0.1: return 'Negative'
|
| return 'Neutral'
|
|
|
| reviews_df['Sentiment_Label'] = reviews_df['Sentiment_Score'].apply(label_sentiment)
|
| return reviews_df
|
|
|
