Update app.py

app.py

@@ -70,14 +70,14 @@ for (colname, colval) in uncleaned_data.iteritems():
   
   cat_value_dicts[colname] = new_dict
   data[colname] = transformed_col_vals
-    
-    
-  ### -------------------------------- ###
-  ###           model training         ###
-  ### -------------------------------- ###
-  
+
+
+### -------------------------------- ###
+###           model training         ###
+### -------------------------------- ###
+
 def train_model():
-  # select features and predicton; automatically selects last column as prediction
+  # select features and prediction; automatically selects last column as prediction
   cols = len(data.columns)
   num_features = cols - 1
   x = data.iloc[: , :num_features]
@@ -91,10 +91,11 @@ def train_model():
   model.fit(x_train, y_train.values.ravel())
   y_pred = model.predict(x_test)
   
-  # save the model to file
+  # save the model to file using the pickle package
   with open('model.pkl', 'wb') as f:
     pkl.dump(model, f)
   
+  # save model accuracy to file using the pickle package
   with open('acc.txt', 'w+') as f:
     acc = metrics.accuracy_score(y_test, y_pred)
     f.write(str(round(acc * 100, 1)) + '%')
@@ -105,24 +106,28 @@ def train_model():
 ###            rerun logic           ###
 ### -------------------------------- ###
 
+# check to see if this is the first time running the script,
+# if the model has already been trained and saved, load it
 try:
   with open('model.pkl', 'rb') as f:
     model = pkl.load(f)
+    
+# if this is the first time running the script, train the model
+# and save it to the file model.pkl
 except FileNotFoundError as e:
   model = train_model()
 
+# read the model accuracy from file
 with open('acc.txt', 'r') as f:
   acc = f.read()
 
 
-
-
 ### ------------------------------- ###
 ###        interface creation       ###
 ### ------------------------------- ###
 
-
-# predictor for generic number of features
+# uses the logistic regression to predict for a generic number
+# of features
 def general_predictor(input_list):
   features = []
 
@@ -140,9 +145,9 @@ def general_predictor(input_list):
 
 def get_feat():
   feats = [abs(x) for x in model.coef_[0]]
-  # max_val = max(feats)
-  # idx = feats.index(max_val)
-  return str(feats) # data.columns[idx]
+  max_val = max(feats)
+  idx = feats.index(max_val)
+  return data.columns[idx]
 
 form = st.form('ml-inputs')
 
@@ -171,7 +176,7 @@ if form.form_submit_button("Submit to get your recommendation!"):
 col1, col2 = st.columns(2)
 col1.metric("Number of Different Possible Results", len(cat_value_dicts[final_colname]))
 col2.metric("Model Accuracy",  acc)
-# st.metric("Most Important Question", get_feat())
+st.metric("Most Important Question", get_feat())
 
   
 with open('info.md') as f: