Upload 10 files

app.py

@@ -0,0 +1,29 @@
+import streamlit as st
+import pandas as pd
+from eda import run_eda_app
+from prediction import run_prediction_app
+import matplotlib.pyplot as plt
+
+# Load the dataset
+data = pd.read_csv('online_shoppers_intention.csv')
+
+# Main app
+def main():
+    st.title('Online Shoppers Intention Prediction App')
+    
+    # Sidebar for navigation
+    menu = ['Home', 'EDA', 'Prediction']
+    choice = st.sidebar.selectbox('Menu', menu)
+    
+    if choice == 'Home':
+        st.write('Welcome to the Online Shoppers Intention Prediction App!')
+        st.write('Navigate to the EDA or Prediction sections using the sidebar to explore further.')
+    
+    elif choice == 'EDA':
+        run_eda_app(data)
+        
+    elif choice == 'Prediction':
+        run_prediction_app()
+
+if __name__ == '__main__':
+    main()

categorical_cols_list.txt

@@ -0,0 +1 @@
+["Month", "VisitorType", "Weekend"]

eda.py

@@ -0,0 +1,34 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+def run_eda_app(data):
+    st.subheader('Exploratory Data Analysis')
+    
+    # Display data
+    st.write("Here's a glimpse of the dataset:")
+    st.write(data.head())
+    
+    # Show data distribution
+    if st.checkbox('Show data distribution'):
+        st.write('Data distribution:')
+        fig, ax = plt.subplots()
+        data.hist(ax=ax, bins=30, figsize=(20,15))
+        st.pyplot(fig)
+    
+    # Correlation heatmap
+    if st.checkbox('Show correlation heatmap'):
+        st.write('Correlation heatmap:')
+        fig, ax = plt.subplots(figsize=(10,8))
+        sns.heatmap(data.corr(), annot=True, cmap='coolwarm', ax=ax)
+        st.pyplot(fig)
+
+    # Monthly distribution of sessions
+    if st.checkbox('Show monthly distribution of sessions'):
+        st.write('Monthly distribution of sessions:')
+        fig, ax = plt.subplots(figsize=(10,6))
+        data['Month'].value_counts().plot(kind='bar', ax=ax)
+        ax.set_title('Number of sessions per month')
+        ax.set_ylabel('Count')
+        st.pyplot(fig)

encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d6537db61c0edfa4a5b16853d6a8fc5147eeca697548626525cb0a9177b70b
+size 868

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8691e7dafeb9f9e8a38bdd2a46958d7741811747cb7d6db99d32cb176b000a
+size 33484083

numerical_cols_list.txt

@@ -0,0 +1 @@
+["Administrative", "Administrative_Duration", "Informational", "Informational_Duration", "ProductRelated", "ProductRelated_Duration", "BounceRates", "ExitRates", "PageValues", "SpecialDay", "OperatingSystems", "Browser", "Region", "TrafficType"]

prediction.py

@@ -0,0 +1,55 @@
+import streamlit as st
+import numpy as np
+import pickle
+
+# Load the trained Random Forest classifier
+with open('model.pkl', 'rb') as file:
+    model = pickle.load(file)
+
+def run_prediction_app():
+    st.subheader('Predict Revenue Generation')
+    
+    # Taking input from the user
+    Administrative = st.number_input('Administrative', value=0)
+    Administrative_Duration = st.number_input('Administrative Duration', value=0.0)
+    Informational = st.number_input('Informational', value=0)
+    Informational_Duration = st.number_input('Informational Duration', value=0.0)
+    ProductRelated = st.number_input('ProductRelated', value=0)
+    ProductRelated_Duration = st.number_input('ProductRelated Duration', value=0.0)
+    BounceRates = st.number_input('BounceRates', value=0.0)
+    ExitRates = st.number_input('ExitRates', value=0.0)
+    PageValues = st.number_input('PageValues', value=0.0)
+    SpecialDay = st.number_input('SpecialDay', value=0.0)
+    Month = st.selectbox('Month', ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'June', 'July', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])
+    OperatingSystems = st.number_input('Operating Systems', value=1)
+    Browser = st.number_input('Browser', value=1)
+    Region = st.number_input('Region', value=1)
+    TrafficType = st.number_input('Traffic Type', value=1)
+    VisitorType = st.selectbox('Visitor Type', ['Returning_Visitor', 'New_Visitor', 'Other'])
+    Weekend = st.checkbox('Weekend?')
+    
+    # When 'Predict' is clicked, make the prediction and store it 
+    if st.button('Predict'):
+        input_data = {
+            'Administrative': Administrative,
+            'Administrative_Duration': Administrative_Duration,
+            'Informational': Informational,
+            'Informational_Duration': Informational_Duration,
+            'ProductRelated': ProductRelated,
+            'ProductRelated_Duration': ProductRelated_Duration,
+            'BounceRates': BounceRates,
+            'ExitRates': ExitRates,
+            'PageValues': PageValues,
+            'SpecialDay': SpecialDay,
+            'Month': Month,
+            'OperatingSystems': OperatingSystems,
+            'Browser': Browser,
+            'Region': Region,
+            'TrafficType': TrafficType,
+            'VisitorType': VisitorType,
+            'Weekend': Weekend
+        }
+        
+        # Make prediction
+        prediction = model.predict([list(input_data.values())])[0]
+        st.write(f"Prediction: {'Revenue' if prediction else 'No Revenue'}")

requirement.txt

@@ -0,0 +1,7 @@
+streamlit
+pandas
+seaborn
+matplotlib
+numpy
+scikit-learn
+plotly

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ceaaf7cab937c6bd3e17e87df18b70cf7126c4da35037e95d6c2ce02c5557ae
+size 1103