RFM Müşteri Segmentasyonu Zor mu Pandas AI

You are Pandas AI expert. Load customer dataset from [file_path] as df. Assume columns: [customer_id], [date_column] (ISO format), [amount_column]. Today is current date. Step 1: Compute RFM - Recency: days since last purchase (use [recency_days] as analysis window, e.g., 365), group by [customer_id] for min days to today. Frequency: count of purchases per [customer_id]. Monetary: sum of [amount_column] per [customer_id]. Create rfm_df with these scores. Step 2: Segment using quartiles: R_score = pd.qcut(recency, 4, labels=[4,3,2,1]), F_score/M_score similar (higher better). RFM_score = 100*R + 10*F + M. Segment: if R>=4 & F>=4 & M>=4: 'Champions'; R>=3 & F>=3: 'Loyal'; R=3: 'At Risk'; etc. (define 8 segments). Step 3: Analyze: top segments by avg monetary, count %. Step 4: Visualize: rfm scatterplot (F vs M colored by R), barplot of segment sizes. Export segments to 'rfm_segments.csv'. Use practical e-commerce example: recent 30-day recency for churn prediction. Show code and results.

You are Pandas AI expert. Load customer dataset from [file_path] as df. Assume columns: [customer_id], [date_column] (ISO format), [amount_column]. Today is current date. Step 1: Compute RFM - Recency: days since last purchase (use [recency_days] as analysis window, e.g., 365), group by [customer_id] for min days to today. Frequency: count of purchases per [customer_id]. Monetary: sum of [amount_column] per [customer_id]. Create rfm_df with these scores. Step 2: Segment using quartiles: R_score = pd.qcut(recency, 4, labels=[4,3,2,1]), F_score/M_score similar (higher better). RFM_score = 100*R + 10*F + M. Segment: if R>=4 & F>=4 & M>=4: 'Champions'; R>=3 & F>=3: 'Loyal'; R=3: 'At Risk'; etc. (define 8 segments). Step 3: Analyze: top segments by avg monetary, count %. Step 4: Visualize: rfm scatterplot (F vs M colored by R), barplot of segment sizes. Export segments to 'rfm_segments.csv'. Use practical e-commerce example: recent 30-day recency for churn prediction. Show code and results.