Upload 4 files

app.py

@@ -0,0 +1,110 @@
+import streamlit as st
+import joblib
+import numpy as np
+import pandas as pd
+import plotly.express as px
+
+# Load the models
+scaler = joblib.load('scaler.joblib')
+model = joblib.load('best_rf.joblib')
+
+sensory_feature_column = ['sweet',
+ 'sour',
+ 'bitter',
+ 'aromatic_impact',
+ 'fruity_impact',
+ 'art_sweetener_chewing',
+ 'chews',
+ 'art_sweetener_after',
+ 'stickiness_with_fingers',
+ 'springiness_with_fingers',
+ 'abrasive',
+ 'hardness_with_molars',
+ 'uniformity_of_bite',
+ 'gritty',
+ 'springiness_during_chew',
+ 'cohesiveness_of_mass',
+ 'moistness_of_mass',
+ 'toothsticking',
+ 'toothpacking',
+ 'adhesiveness_to_molars',
+ 'oily_mouthcoating']
+
+def scale_output(prediction_matrix):
+    # Calculate the sum for each row
+    row_sums = np.sum(prediction_matrix, axis=1)
+
+    # Calculate the surplus or lack from 1 for each row
+    delta = 1 - row_sums
+
+    # Adjust each row proportionally
+    adjusted_matrix = prediction_matrix + delta[:, np.newaxis] * (prediction_matrix / row_sums[:, np.newaxis])
+    print(f'scaled probability: {adjusted_matrix.sum(axis=1)}')
+    return adjusted_matrix
+
+# Streamlit App
+def main():
+    st.title("User distribution prediction")
+    
+    col1, col2, col3 = st.columns(3)
+    
+    with col1:
+        sweet = st.slider('sweet', 0.00, 10.00, 0.01)
+        aromatic_impact = st.slider('aromatic impact', 0.00, 10.00, 0.01)
+        chew = st.slider('chew', 0.00, 10.00, 0.01)
+        springiness_with_fingers = st.slider('springiness_with_fingers', 0.00, 10.00, 0.01)
+        uniformity_of_bite = st.slider('uniformity_of_bite', 0.00, 10.00, 0.01)
+        cohesiveness_of_mass = st.slider('cohesiveness_of_mass', 0.00, 10.00, 0.01)
+        toothpacking = st.slider('toothpacking', 0.00, 10.00, 0.01)
+        
+    with col2:
+        sour = st.slider('sour', 0.00, 10.00, 0.01)
+        fruity_impact = st.slider('fruity impact',0.00, 10.00, 0.01)
+        art_sweetener_after = st.slider('art_sweetener_after', 0.00, 10.00, 0.01)
+        abrasiveness = st.slider('abrasiveness', 0.00, 10.00, 0.01)
+        gritty = st.slider('gritty', 0.00, 10.00, 0.01)
+        moisture_of_mass = st.slider('moisture_of_mass', 0.00, 10.00, 0.01)
+        adhesiveness_to_molars = st.slider('adhesiveness_to_molars', 0.00, 10.00, 0.01)
+
+
+    with col3:
+        bitter = st.slider('bitter',  0.00, 10.00, 0.01)
+        art_sweetener_chewing = st.slider('art_sweetener_chewing',0.00, 10.00, 0.01)
+        stickiness_with_fingers = st.slider('stickiness_with_fingers', 0.00, 10.00, 0.01)
+        hardness_with_molars = st.slider('hardness_with_molars', 0.00, 10.00, 0.01)
+        springiness_during_chew = st.slider('springiness_during_chew', 0.00, 10.00, 0.01)
+        toothsticking = st.slider('toothsticking', 0.00, 10.00, 0.01)
+        oily_mouthcoating = st.slider('oily_mouthcoating', 0.00, 10.00, 0.01)
+
+
+    data_input = [sweet, sour, bitter, aromatic_impact, fruity_impact, art_sweetener_chewing,chew,
+                 art_sweetener_after, stickiness_with_fingers,  springiness_with_fingers , abrasiveness,  hardness_with_molars , uniformity_of_bite, gritty,
+                 springiness_during_chew, cohesiveness_of_mass, moisture_of_mass , toothsticking , toothpacking, adhesiveness_to_molars, oily_mouthcoating]
+
+    test_df = pd.DataFrame(np.array(data_input).reshape(1, 21))
+    test_df.columns = sensory_feature_column
+    
+    scaled_data_input = scaler.transform(test_df)
+    handout_prediction = scale_output(model.predict(scaled_data_input))
+    
+    handout_pred_df = pd.DataFrame(handout_prediction)
+    handout_pred_df.columns = [str(i) for i in range(1,10)]
+    handout_pred_df['prod'] = 'prediction'
+    handout_pred_df = handout_pred_df.melt('prod')
+    # handout_pred_df['type'] = 'handout_test'
+    
+    # st.write(f"select data: {data_input  }")
+    # st.write(f"scaled select data: {scaled_data_input  }")
+    st.write(f"prediction: {handout_prediction  }")
+    st.write(f"sum of probability: {handout_prediction.sum()}")
+    
+    fig = px.histogram(data_frame=handout_pred_df, x= 'variable',y='value', nbins= 9,
+                     text_auto=True, title="Probability prediction of liking score from sensory attributes",
+                labels={"value": "probability",
+                      "variable": "liking score"})
+                
+    st.plotly_chart(fig, theme='streamlit')
+    
+
+if __name__ == "__main__":
+    main()

best_rf.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9628ee04279903b0435981063ef25122a1a573ba8d79a34f2f801cdfcf96713
+size 1775335

requirements.txt

@@ -0,0 +1,10 @@
+pandas
+pyxlsb
+seaborn
+plotly
+nbformat
+ipykernel
+scikit-learn
+statsmodels
+streamlit
+shap

scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b292c973e27df674137f95577e6a1283ff70daf9e50965eff31a174962314235
+size 2277