feat: Add support for "Offers - IDs only" type in compute_offer function

app.py

@@ -14,10 +14,10 @@ PASS = os.getenv("PASSWORD")
 # create an interface and limit output's width for the dataframe bu
 list_iface = gr.Interface(fn=compute_offer,
             inputs=[gr.File(label="Upload CSV", type="file"),
-                    gr.Slider(1, 365, value=3, step=1, label="Days", info="Number of days to look back"),
+                    gr.Slider(0, 365, value=3, step=1, label="Days", info="Number of days to look back"),
                     gr.Slider(5000, 10000000, value=1000000, step=1, label="Minimum Sent", info="Minimum number of emails sent"),
                     gr.Dropdown(["Comcast", "Yahoo", "Hotmail", "Aol"], value="Yahoo", label="Domain"),
-                    gr.Radio(["Newsletters", "Offers"], label="Type", value="Offers"),
+                    gr.Radio(["Newsletters", "Offers", 'Offers - IDs only'], label="Type", value="Offers - IDs only"),
                     gr.Textbox(label="Exclude list", info="Example: INH,MNP", value="INH,DHI,HHP,RTA,JVR,HTH,FNC,SCD,ENH,WIP")],
             outputs="dataframe")
 

utils/gradio_utils.py

@@ -283,7 +283,7 @@ def compute_offer(csv_file, days_lookback, min_sent, domain, offer_type, x_list)
                         (df_all['Nume'].str.contains(r' \d{4}$')) & \
                         (~df_all['Nume'].str.contains('TRIMITE'))
                         ]
-    elif offer_type == "Offers":
+    elif offer_type == "Offers" or offer_type == "Offers - IDs only":
         df_all = df_all[~df_all['Nume'].str.startswith("Aeon News")]
         df_all = df_all[~df_all['Nume'].str.contains("NU SE TRIMITE")]
         df_all = df_all[~df_all['Nume'].str.contains("de testat")]
@@ -304,16 +304,26 @@ def compute_offer(csv_file, days_lookback, min_sent, domain, offer_type, x_list)
 
     if offer_type == "Newsletters":
         final_df = df_all.groupby(["Oferta", "Nume"])\
-            .agg( N=('Oferta', 'count'), send_avg=('Send', 'mean'), CO=('Click Open', 'mean'))\
-            .sort_values(['CO', 'N'], ascending=False)
+            .agg( times_sent=('Oferta', 'count'), send_avg=('Send', 'mean'), CO=('Click Open', 'mean'))\
+            .sort_values(['CO', 'times_sent'], ascending=False)
         final_df['send_avg'] = final_df['send_avg'].astype(int)
         final_df['CO'] = final_df['CO'].round(2).astype(float)
         final_df.reset_index(inplace=True)
     elif offer_type == "Offers":
         final_df = df_all.groupby(["Oferta", "Nume"])\
-            .agg( N=('Oferta', 'count'), send_avg=('Send', 'mean'), ECPM=('ECPM', 'mean'))\
-            .sort_values(['ECPM', 'N'], ascending=False)
+            .agg( times_sent=('Oferta', 'count'), send_avg=('Send', 'mean'), ECPM=('ECPM', 'mean'))\
+            .sort_values(['ECPM', 'times_sent'], ascending=False)
         final_df['send_avg'] = final_df['send_avg'].astype(int)
         final_df['ECPM'] = final_df['ECPM'].round(2).astype(float)
         final_df.reset_index(inplace=True)
+    elif offer_type == "Offers - IDs only":
+        df_all['offer_id'] = df_all['Nume'].str.extract(r'(\d{3,4}$)')
+        final_df = df_all.groupby(["offer_id"])\
+            .agg( times_sent=('offer_id', 'count'), send_avg=('Send', 'mean'), ECPM=('ECPM', 'mean'))\
+            .sort_values(['ECPM', 'times_sent'], ascending=False)
+        final_df['send_avg'] = final_df['send_avg'].astype(int)
+        final_df['ECPM'] = final_df['ECPM'].round(2).astype(float)
+        final_df.reset_index(inplace=True)
+    else:
+        final_df = pd.DataFrame()
     return final_df