wip_model output working

app.py

@@ -5,6 +5,8 @@ import PIL
 import re
 from io import StringIO
 import boto3
+from urlextract import URLExtract
+
 
 # from joblib import dump, load
 
@@ -13,9 +15,6 @@ import joblib
 from bokeh.models.widgets import Div
 
 import email
-from urlextract import URLExtract
-
-import main_app
 
 
 def table_data():
@@ -105,13 +104,6 @@ def email_body_extractor(email_data):
 
     return body, character_cnt, url_cnt
 
-# def select_char_preference_variables():
-#     opt_list = ["Increase", "Decrease"]
-#     button_option = widgets.RadioButtons(options = opt_list)
-#     print("Do you want to increase or decrease your character count in the email?")
-#     display(button_option)
-#     return button_option
-
 
 def add_bg_from_url():
     st.markdown(
@@ -215,26 +207,30 @@ if uploaded_file is None:
 
 industry = st.selectbox(
     'Please select your industry',
-    industry_lists
+    industry_lists,
+    index=6
 )
 
 campaign  = st.selectbox(
     'Please select your industry',
-    campaign_types
+    campaign_types,
+    index=5
 )
 
 target = st.selectbox(
     'Please select your target variable',
-    target_variables
+    target_variables,
+    index=1
 )
 
 st.markdown("""---""")
 
 char_reco_preference = st.selectbox(
     'Do you want to increase or decrease your character count in the email?',
-    ["Increase", "Decrease"])
-
+    ["Increase", "Decrease"],
+    index=1)
 
+st.cache()
 def get_files_from_aws(bucket,prefix):
     """
         get files from aws s3 bucket
@@ -255,6 +251,7 @@ def get_files_from_aws(bucket,prefix):
     return df 
 
 
+# st.info([industry,campaign,target,char_reco_preference])
 
 
 if st.button('Generate Predictions'):
@@ -266,7 +263,6 @@ if st.button('Generate Predictions'):
 
         # Starting predictions
         model = joblib.load('models/models.sav')
-        print(type(model))
         # Generate Email Data
         email_data = get_files_from_aws('emailcampaigntrainingdata','trainingdata/email_dataset_training.csv')
         acc_data = get_files_from_aws('emailcampaigntrainingdata','trainingdata/email_dataset_training_raw.csv')
@@ -282,7 +278,6 @@ if st.button('Generate Predictions'):
 
         
         industry_code_dict = get_industry_code_dict(email_data)
-
         bytes_data = uploaded_file.getvalue()
 
         email_body, character_cnt, url_cnt = email_body_extractor(bytes_data)
@@ -296,48 +291,67 @@ if st.button('Generate Predictions'):
         df_uploaded["industry_code"] = industry_code_dict.get(industry)
         df_uploaded_test = df_uploaded[["industry_code", "character_cnt", "url_cnt"]]
         predicted_rate =  model.predict(df_uploaded_test)[0]
-        output_rate = round(predicted_rate*100,2)
-        print(output_rate)
-        # output_rate = 0.5
+        output_rate = round(predicted_rate,4)
+
         if output_rate < 0:
             print("Sorry, Current model couldn't provide predictions on the target variable you selected.")
         else:
-            st.info('Current Character Count in Your Email is: {}'.format(character_cnt))
-            st.info('The model predicts that it achieves a {} of {}%'.format(target, str(output_rate)))
-            
-            # print(target)
+            st.markdown('### Current Character Count in Your Email is: <span style="color:blue">{}</span>'.format(character_cnt), unsafe_allow_html=True)
+            # st.info('The model predicts that it achieves a {} of {}%'.format(target, str(round(output_rate*100,2))))
+            if target == 'conversion_rate':
+                target_vis = 'Conversion Rate'
+            else:
+                target_vis = 'Click-to-Open Rate'
+            st.markdown('### The model predicts that it achieves a <span style="color:blue">{}</span> of {}%'.format(target_vis, str(round(output_rate*100,2))),unsafe_allow_html=True)
+            selected_industry_code = industry_code_dict.get(industry)
+
             if target == "click_to_open_rate":
                 selected_variable = "Open_Rate"
             if target == "conversion_rate":
                 selected_variable = "Click_Through_Rate"
 
+
             df_reco = training_dataset[["industry_code", "character_cnt", "url_cnt", selected_variable]]  
-            df_reco = df_reco[df_reco["industry_code"] == industry]
+            df_reco = df_reco[df_reco["industry_code"] == selected_industry_code]
             df_reco[selected_variable]=df_reco[selected_variable].apply(lambda x:round(x, 3))
             df_reco_sort = df_reco.sort_values(by=[selected_variable])
             df_reco = df_reco.drop_duplicates(subset=selected_variable)
 
-            if char_reco_preference == "Increase":
+            preference = char_reco_preference
+            if preference == "Increase":
                 df_reco_opt = df_reco[(df_reco[selected_variable] > output_rate) & (df_reco["character_cnt"] > character_cnt) & (df_reco["character_cnt"] <= (1.5*character_cnt))]
                 df_reco_opt_rank = df_reco_opt.nlargest(3,[selected_variable])
-            else:
+            ## decrease character reco
+            if preference == "Decrease":
                 df_reco_opt = df_reco[(df_reco[selected_variable] > output_rate) & (df_reco["character_cnt"] < character_cnt)]
                 df_reco_opt_rank = df_reco_opt.nlargest(3,[selected_variable])
-                
+            
+
+            # something wrong here    
+            # if char_reco_preference == "Increase":
+            #     df_reco_opt = df_reco[(df_reco[selected_variable] > output_rate) & (df_reco["character_cnt"] > character_cnt) & (df_reco["character_cnt"] <= (1.5*character_cnt))]
+            #     df_reco_opt_rank = df_reco_opt.nlargest(3,[selected_variable])
+            # if char_reco_preference == "Decrease":
+            #     df_reco_opt = df_reco[(df_reco[selected_variable] > output_rate) & (df_reco["character_cnt"] < character_cnt)]
+            #     df_reco_opt_rank = df_reco_opt.nlargest(3,[selected_variable])
+  
+            # print(df_reco_opt)
+            # print(df_reco_opt_rank)
+
             if selected_variable == "Open_Rate":
                 selected_variable = "Click-to-Open_Rate"
             if selected_variable == "Click_Through_Rate":
                 selected_variable = "Conversion_Rate"
 
-            st.info('To get higher, {},the model recommends the following options:'.format(selected_variable))
+            st.markdown('### To get higher, <span style="color:blue">{}</span>,the model recommends the following options:'.format(selected_variable),unsafe_allow_html=True)
             if len(df_reco_opt_rank) == 0:
-                st.info('You ve already achieved the highest, {}, with the current character count!'.format(selected_variable))
+                st.info('You ve already achieved the highest, <span style="color:blue">{}</span>, with the current character count!'.format(selected_variable),unsafe_allow_html=True)
             else:
                 for _, row in df_reco_opt_rank.iterrows():
                     Character_Count = row[1]
                     selected_variable = row[3]
                     # print(f"·Number of Characters: {int(Character_Count)}, Target Rate: {round(selected_variable, 3)*100}", "%")
-                    st.info('Number of Characters: {}, Target Rate: {}'.format(int(Character_Count), round(selected_variable, 3)*100))
+                    st.markdown('#### Number of Characters: {}, Target Rate: {}'.format(int(Character_Count), round(selected_variable*100, 3)))
 
 
         placeholder.empty()