clean up the model a little bit

app.py

@@ -6,8 +6,7 @@ import re
 from io import StringIO
 import boto3
 from urlextract import URLExtract
-
-
+import time
 # from joblib import dump, load
 
 import joblib
@@ -230,7 +229,7 @@ char_reco_preference = st.selectbox(
     ["Increase", "Decrease"],
     index=1)
 
-st.cache()
+
 def get_files_from_aws(bucket,prefix):
     """
         get files from aws s3 bucket
@@ -255,6 +254,7 @@ def get_files_from_aws(bucket,prefix):
 
 
 if st.button('Generate Predictions'):
+    start_time = time.time()
     if uploaded_file is None:
         st.error('Please upload a email (HTML format)')
     else:
@@ -273,9 +273,10 @@ if st.button('Generate Predictions'):
 
         # Dataset:
         training_dataset = get_files_from_aws('emailcampaigntrainingdata','modelCC/training.csv')
-        X_test = get_files_from_aws('emailcampaigntrainingdata','modelCC/Xtest.csv')
-        Y_test = get_files_from_aws('emailcampaigntrainingdata','modelCC/ytest.csv')
+        # X_test = get_files_from_aws('emailcampaigntrainingdata','modelCC/Xtest.csv')
+        # Y_test = get_files_from_aws('emailcampaigntrainingdata','modelCC/ytest.csv')
 
+        # print("Getting Data Time: %s seconds" % (time.time() - start_time))
         
         industry_code_dict = get_industry_code_dict(email_data)
         bytes_data = uploaded_file.getvalue()
@@ -293,16 +294,17 @@ if st.button('Generate Predictions'):
         predicted_rate =  model.predict(df_uploaded_test)[0]
         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.markdown('### Current Character Count in Your Email is: <span style="color:blue">{}</span>'.format(character_cnt), unsafe_allow_html=True)
+            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)
+            st.markdown('#### The model predicts that it achieves a <span style="color:blue">{}</span> of <span style="color:blue">{}</span>%'.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":
@@ -325,33 +327,23 @@ if st.button('Generate Predictions'):
             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.markdown('### To get higher, <span style="color:blue">{}</span>,the model recommends the following options:'.format(selected_variable),unsafe_allow_html=True)
+            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, <span style="color:blue">{}</span>, with the current character count!'.format(selected_variable),unsafe_allow_html=True)
+                st.markdown('#### 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.markdown('#### Number of Characters: {}, Target Rate: {}'.format(int(Character_Count), round(selected_variable*100, 3)))
+                    st.markdown('Number of Characters: {}, Target Rate: {}'.format(int(Character_Count), round(selected_variable*100, 3)))
 
 
-        placeholder.empty()
+        placeholder.empty()
+        # print(time.time() - start_time)