Duplicate from Jhoeel/rfmAutoV2

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: RfmAuto
+emoji: 💩
+colorFrom: indigo
+colorTo: red
+sdk: gradio
+sdk_version: 3.19.1
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: Jhoeel/rfmAutoV2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,72 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+import datetime
+from sklearn.preprocessing import StandardScaler
+from sklearn.cluster import KMeans
+
+def calculate_rfm(df):
+    # Convert 'Fecha compra' to datetime and calculate recency
+    df['Fecha compra'] = pd.to_datetime(df['Fecha compra'], format='%m/%d/%Y')
+    today = datetime.datetime.now().date()
+    fecha_actual = pd.to_datetime(today).to_numpy().astype('datetime64[D]')
+    df['recencia'] = (fecha_actual - df['Fecha compra'].to_numpy().astype('datetime64[D]'))
+    df['recencia'] = df['recencia'].astype('timedelta64[D]').astype(int)
+
+    # Group by 'Email' and calculate frequency and monetary value
+    grouped = df.groupby('Email')
+    frequency = grouped['Email'].count().to_frame().rename(columns={"Email": "frecuencia"})
+    monetary = grouped['Valor compra'].sum().to_frame().rename(columns={'Valor compra': 'monetario'})
+    monetary['monetario'] = monetary['monetario'].round(2)
+
+    # Join the recency dataframe with frequency and monetary dataframes
+    df = df.join(frequency, on='Email')
+    df = df.join(monetary, on='Email')
+
+    # Keep only the latest purchase for each customer
+    df = df.sort_values(by=['Email', 'Fecha compra'], ascending=False)
+    df = df.drop_duplicates(subset='Email', keep='first')
+
+    # Clean up the final dataframe
+    df.drop(['Fecha compra', 'Valor compra'], axis=1, inplace=True)
+    df.set_index('Email', inplace=True)
+
+    # Scale the features
+    scaler = StandardScaler()
+    scaled_columns = ['recencia', 'frecuencia', 'monetario']
+    scaled_values = scaler.fit_transform(df[scaled_columns])
+    z_scores = np.abs(scaled_values)
+    outlier_mask = (z_scores > 3).any(axis=1)
+
+    for i, column in enumerate(scaled_columns):
+        df[f"{column}_scaled"] = scaled_values[:, i]
+
+    df = df[~outlier_mask]
+
+    # Cluster the data
+    np.random.seed(0)
+    scaled_columns = ['recencia_scaled', 'frecuencia_scaled', 'monetario_scaled']
+    kmeans = KMeans(n_clusters=5, n_init=10)
+    rfm_clusters = kmeans.fit_predict(df[scaled_columns])
+    df = df.copy()
+    df['cluster'] = rfm_clusters
+
+    # Drop the scaled columns
+    df.drop(scaled_columns, axis=1, inplace=True)
+
+    # Reset the index
+    df = df.reset_index()
+
+    # Return the desired columns
+    return df[['Email', 'recencia', 'frecuencia', 'monetario', 'cluster']]
+
+
+def read_csv(file):
+    df = pd.read_csv(file.name)
+    return calculate_rfm(df)
+
+iface = gr.Interface(fn=read_csv, 
+                     inputs=[gr.inputs.File(label="Select a CSV file")], 
+                     outputs="dataframe")
+
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+pandas
+scikit-learn