Create app.py

app.py

@@ -0,0 +1,113 @@
+%%writefile app.py
+import joblib
+import pandas as pd
+import numpy as np
+import streamlit as st
+from sklearn.preprocessing import LabelEncoder
+from lime.lime_tabular import LimeTabularExplainer
+
+# -------------------------------------------------------------------------------------
+df = pd.read_csv(r"C:\Users\bhati\Documents\MachineLearning\FreelanceProject\StudentPerformance\combined.csv", index_col=0)
+df2 = df.copy()
+obj_columns = df.select_dtypes(include=['object']).columns
+num_columns = df.select_dtypes(include='number').columns
+le_dict = {}
+classes_dict = {}
+for col in obj_columns:
+    le = LabelEncoder()
+    df2[col] = le.fit_transform(df[col])
+    le_dict[col] = le
+    classes_dict[col] = le.classes_
+df2['G1'] = df2.pop('G1')
+df2['G2'] = df2.pop('G2')
+df2['G3'] = df2.pop('G3')
+X = df2.iloc[:,:-1]
+y = df2.iloc[:,-1]
+allCol = X.columns
+
+# -------------------------------------------------------------------------------------
+# Load the model from the file
+joblib_file = "xgb_model.joblib"
+loaded_model = joblib.load(joblib_file)
+
+# -------------------------------------------------------------------------------------
+variableExpl = []
+with open(r'C:\Users\bhati\Documents\MachineLearning\FreelanceProject\StudentPerformance\student.txt', 'r', encoding='utf-8') as file:
+    for line in file:
+        cleaned_line = line.strip()
+        # Append each cleaned line as a row to the list
+        variableExpl.append(cleaned_line)
+
+variableExpl.pop(0)
+for i in range(5):
+    variableExpl.pop(-1)
+for i in range(2):
+    variableExpl.pop(-3)
+
+variableExplDict = {}
+for i in variableExpl:
+    variableExplDict[i.split()[1]] = i
+
+# -------------------------------------------------------------------------------------
+def predict_score(inputs):
+    if any(value == '' for value in inputs):
+        return "Please enter all the inputs."
+        
+    #-------------------------------------------------------------------------------------------
+    # Create a dictionary for each input
+    input_df = pd.DataFrame(np.array(inputs).reshape(1, -1), columns=allCol)
+
+
+    #-------------------------------------------------------------------------------------------
+    # label encode each input
+    for col in obj_columns:
+        if col in input_df.columns:
+             input_df[col] = le_dict[col].transform(input_df[col])
+    
+    #-------------------------------------------------------------------------------------------
+    # Make predictions
+    pred = loaded_model.predict(input_df)
+
+    # Ensure all columns are numeric
+    input_df = input_df.astype(float)
+    #-------------------------------------------------------------------------------------------
+    # Create a LIME explainer
+    explainer = LimeTabularExplainer(training_data=X.values, mode="regression", feature_names=allCol, verbose=True)
+
+    exp = explainer.explain_instance(data_row=input_df.iloc[0].to_numpy(), predict_fn=loaded_model.predict, num_features=33)
+
+    impacts = {}
+    for item in exp.as_list():
+        impacts[item[0]] = item[1]
+
+    explTable = pd.DataFrame(np.array(list(impacts.values())).reshape(1,-1), columns=impacts.keys()).T
+    explTable = explTable.rename(columns={0: 'ImpactOnPrediction'})
+    explTable['Positive/Negative'] = explTable['ImpactOnPrediction'].apply(lambda x: 'Negative' if x < 0 else 'Positive')
+
+    return pred, explTable
+
+#-------------------------------------------------------------------------------------------
+# Streamlit app
+st.title("Student's Final Grade Prediction")
+
+# Input
+inputs = []
+for variable in variableExplDict:
+    st.write(variableExplDict[variable])
+    if variable in obj_columns:
+        value = st.selectbox(variable, classes_dict[variable], key=variable)  # Create a dropdown menu
+    else:
+        value = st.text_input(variable, key=variable)
+    inputs.append(value)
+    
+# Predict button
+if st.button("Predict"):
+    score, explantn = predict_score(inputs)
+    st.write("Prediction: ", score)
+    st.write("Impact on prediction:", explantn)
+
+# Clear button functionality
+if st.button("Clear"):
+    st.experimental_rerun()
+
+!streamlit run app.py