Update app.py

app.py

@@ -25,7 +25,7 @@ bb_df = pd.read_csv('beer_brewery_imputed.csv')
 bb_df_percentile = pd.read_csv('bb_df_testing.csv')
                             
 #Set up DF for Aslin Examples
-aslin_example_df_full = pd.read_csv('App_Example_Aslin.csv')
+aslin_example_df_full = pd.read_csv('App_Example_Aslin_Brewery_Update.csv')
 aslin_example_df = aslin_example_df_full.drop(['Number of Ratings Beer'], axis=1)
 aslin_example_df['ABV'] = aslin_example_df['ABV']*100
 
@@ -36,14 +36,14 @@ with open('unique_brewery_file.pickle', 'rb') as file:
     
     
 # load the regressor model from disk
-loaded_model_regressor = pickle.load(open("XGB_Untappd_regressor_FlavorBreakout.pkl", 'rb'))
+loaded_model_regressor = pickle.load(open("XGB_Untappd_regressor_Brewery_Final.pkl", 'rb'))
 # load the classification model from disk
-loaded_model = pickle.load(open("XGB_Untappd_4_classifier_FlavorBreakout.pkl", 'rb'))
+loaded_model = pickle.load(open("XGB_Untappd_4_classifier_Brewery_Final.pkl", 'rb'))
 
 
 #Categorical Variable Encoder
-loaded_enc_regressor = pickle.load(open("target_encoder_regressor_flavorbreakout.pkl", 'rb'))
-loaded_enc_classification = pickle.load(open("target_encoder_classification_flavorbreakout.pkl", 'rb'))
+loaded_enc_regressor = pickle.load(open("target_encoder_regressor_brewery_final.pkl", 'rb'))
+loaded_enc_classification = pickle.load(open("target_encoder_classification_brewery_final.pkl", 'rb'))
 
 #Define Choices
 region_choices = ['Far West','Great Lakes','Mideast','Non-Con','Northeast','OTHER','Plains','Rocky Mountain','Southeast','Southwest']
@@ -103,6 +103,15 @@ hops_list = ['Amarillo', 'Cascade', 'Centennial', 'Chinook', 'Citra', 'Columbus'
 # Setup SHAP
 explainer = shap.Explainer(loaded_model_regressor) # PLEASE DO NOT CHANGE THIS.
 
+
+#Extract Lists for Examples Function
+def extract_selected_items(row, items_list, prefix):
+    selected_items = []
+    for item in items_list:
+        if row[prefix + item] == 1:  # access the DataFrame column directly with the item name
+            selected_items.append(item)
+    return selected_items
+
 #Set up similar beers function
 def filter_beers(style, state):
     target_abv = 0.03  # Set the target ABV value within the function
@@ -129,13 +138,13 @@ def filter_beers(style, state):
 # percentile_style_overall = 0
 # percentile_style_state = 0
 
-def main_func(BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group):
+def main_func(BeerName, Brewery, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group):
 
     flavors_selected = [flavor for flavor in flavors_list if flavor in Flavor_Group]
     hops_selected = [hop for hop in hops_list if hop in Hop_Group]
 
-    new_row = pd.DataFrame(columns=['ABV', 'IBU', 'Style', 'Brewery Style', 'Region', 'State'] + flavors_list + hops_list)
-    new_row.loc[0] = [float(ABV), float(IBU), Style, BreweryStyle, Region, State] + [1 if flavor in Flavor_Group else 0 for flavor in flavors_list] + [1 if hop in Hop_Group else 0 for hop in hops_list]
+    new_row = pd.DataFrame(columns=['Brewery', 'ABV', 'IBU', 'Style', 'Brewery Style', 'Region', 'State'] + flavors_list + hops_list)
+    new_row.loc[0] = [Brewery, float(ABV), float(IBU), Style, BreweryStyle, Region, State] + [1 if flavor in Flavor_Group else 0 for flavor in flavors_list] + [1 if hop in Hop_Group else 0 for hop in hops_list]
     new_row[['ABV', 'IBU']] = new_row[['ABV', 'IBU']].astype(float)
     new_row['ABV'] = new_row['ABV']/100
     
@@ -188,18 +197,9 @@ def main_func(BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Gro
         f"{nr_state_p} Overall": [percentile_state],
         f"{nr_style_p} in USA": [percentile_style_overall],
         f"{nr_style_p} in {nr_state_p}": [percentile_style_overall]
+
     }    
     
-    # percentile_dict1 = {"Percentile Overall": percentile_overall} 
-    # percentile_dict2 = {f"Percentile {nr_state_p}": percentile_state} 
-    # percentile_dict3 = {f"Percentile {nr_style_p} Overall": percentile_style_overall} 
-    # percentile_dict4 = {f"Percentile {nr_style_p} {nr_state_p}": percentile_style_state} 
-    
-    # #Convert to dataframe
-    # percentile_df = pd.DataFrame(
-    #     { "type": ["USA Overall",f"{nr_state_p} Overall",f"USA by Style {nr_style_p}",f"{nr_state_p} by Style {nr_style_p}"],
-    #       "value": [percentile_overall,percentile_state,percentile_style_overall,percentile_style_state],})
-    
     
 
     return local_plot, similar_beers,score_predict_str,percentile_dict0
@@ -215,12 +215,8 @@ def main_func(BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Gro
 ## Create the UI
 title = "<center><b>🍻 **Untappd Beer Rating Predictor**🍻</b></center>"
 description1 = """
-This app predicts beers scores based on Untappd data pulled in June 2023. <b> Mean Average Error (MAE) of .12</b> and <b> Root Mean Squared Error (RMSE) of .16</b>. 
-The input variables in this model<b> explain 65% of the variation </b>in the Untappd beer score """
-
-# description2 = """
-# To use the app, click on one of the examples, or adjust the values of the seven beer score predictors, and click on Analyze. ✨ 
-# """ 
+This app predicts beers scores based on Untappd data pulled in June 2023. <b> Mean Average Error (MAE) of .09</b> and <b> Root Mean Squared Error (RMSE) of .13</b>. 
+The input variables in this model <b> explain 77% of the variation </b>in the Untappd beer score """
 
 theme = gr.themes.Default()#primary_hue="amber"
 
@@ -234,17 +230,19 @@ with gr.Blocks(title=title, theme = theme) as demo:
     submit_btn1 = gr.Button("Predict")
     with Row():        
         with Column():
-                   
+            
+            
             BeerName = Textbox(label='Beer Name (not required)', value = 'New Beer 1')
+            Brewery = Dropdown(choices=unique_breweries_list, label="Brewery", value='Aslin Beer Company')
             ABV = Slider(label="ABV %", minimum=0, maximum=20, value=4.5, step=.1)
             IBU = Slider(label="IBU", minimum=0.0, maximum=200, value=41, step=1)
-            Style = Dropdown(choices=style_choices, label="Select Beer Style", value='IPA - Session')
-            BreweryStyle = Dropdown(choices=brewery_style_choices, label="Select Brewery Style", value='Micro Brewery')
-            Region = Dropdown(choices=region_choices, label="Select USA Region", value='Far West')
-            State = Dropdown(choices=state_choices, label="Select State", value='CA')
+            Style = Dropdown(choices=style_choices, label="Beer Style", value='IPA - Session')
+            BreweryStyle = Dropdown(choices=brewery_style_choices, label="Brewery Style", value='Regional Brewery')
+            Region = Dropdown(choices=region_choices, label="USA Region", value='Southeast')
+            State = Dropdown(choices=state_choices, label="State", value='GA')
             # Grouped checkboxes
-            Flavor_Group = CheckboxGroup(choices=flavors_list, label="Select Flavors")
-            Hop_Group = CheckboxGroup(choices=hops_list, label="Select Hops")
+            Flavor_Group = CheckboxGroup(choices=flavors_list, label="Flavors")
+            Hop_Group = CheckboxGroup(choices=hops_list, label="Hops")
             
             
         #CREATE OUTPUTS
@@ -255,7 +253,7 @@ with gr.Blocks(title=title, theme = theme) as demo:
             gr.Markdown("<h2><center><b>Prediction Drivers</b></center></h2>")
             local_plot = gr.Plot(label = 'Shap:')
             
-            gr.Markdown("<h2><center><b>Percentiles for Beer</b></center></h2>")
+            gr.Markdown(f"<h2><center><b>Percentiles for Beer </b></center></h2>")
             percentile_dict0 = gr.Label(label ='test', show_label=False)
             
             
@@ -282,21 +280,47 @@ with gr.Blocks(title=title, theme = theme) as demo:
     #Button Click Events
     submit_btn1.click(
         main_func,
-        [BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group],
+        [Brewery,BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group],
         [local_plot,similar_beers,score_predict_str,percentile_dict0],
         api_name="Untappd_Rating_Model")
     
     submit_btn2.click(
         main_func,
-        [BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group],
+        [Brewery,BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group],
         [local_plot,similar_beers,score_predict_str,percentile_dict0],
         api_name="Untappd_Rating_Model1")
+    
+    
 
     #EXAMPLES   
-    example_list = aslin_example_df.values.tolist()
+    #example_list = aslin_example_df.values.tolist()
+    
+    
+    
+        # Create examples
+    examples = []
+    for _, row in aslin_example_df.iterrows():
+        example = []
+
+        # Add other inputs to example here
+        example.append(row['Beer Name'])
+        example.append(row['Brewery'])
+        example.append(row['ABV'])
+        example.append(row['IBU'])
+        example.append(row['Style'])
+        example.append(row['Brewery Style'])
+        example.append(row['Region'])
+        example.append(row['State'])
+
+        # Convert binary columns to lists of selected flavors and hops
+        example.append(extract_selected_items(row, flavors_list, ''))
+        example.append(extract_selected_items(row, hops_list, ''))
+
+        examples.append(example)
+
     gr.Markdown("<h1><center><b>Aslin Beers Example Inputs</b></center></h1>")
-    gr.Examples(example_list[:10],
-                [BeerName, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group], # Flavor_Group, Hop_Group
+    gr.Examples(examples[:10],
+                [BeerName, Brewery, ABV, IBU, Style, BreweryStyle, Region, State, Flavor_Group, Hop_Group], # Flavor_Group, Hop_Group
                 [local_plot, similar_beers, score_predict_str,percentile_dict0], 
                 main_func, 
                 cache_examples=True, label = "Aslin Beer List")