Binary-Classification-Web-App/app.py at main · indrapaul824/Binary-Classification-Web-App · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
import streamlit as st
import numpy as np
import utils

from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier


from sklearn.metrics import precision_score, recall_score

st.set_option('deprecation.showPyplotGlobalUse', False)


def main():
    st.title("Binary Classification Web App")
    st.sidebar.title("Binary Classification Web App")
    st.markdown("Are your mushrooms edible or poisonous? 🍄")
    st.sidebar.markdown("Are your mushrooms edible or poisonous? 🍄")


    df = utils.load_data()
    x_train, x_test, y_train, y_test = utils.split(df)
    class_names = ["edible", "poisonous"]

    st.sidebar.subheader("Choose Classifier")
    classifier = st.sidebar.selectbox("Classifier", ("Support Vector Machine (SVM)", "Logistic Regression",
                                                     "Random Forest Classification"))


    if classifier == 'Support Vector Machine (SVM)':
        st.sidebar.subheader("Model Hyperparameters")
        C = st.sidebar.number_input("C (Regularization parameter)", 0.01, 10.0, step=0.01, key='C')
        kernel = st.sidebar.radio("Kernel", ("rbf", "linear"), key='kernel')
        gamma = st.sidebar.radio("Gamma (Kernel Coefficient)", ("scale", "auto"), key='gamma')

        metrics = st.sidebar.multiselect("What matrix to plot?", ("Confusion Matrix", "ROC Curve",
                                                                  "Precision-Recall Curve"))

        if st.sidebar.button("Classify", key="classify"):
            st.subheader("Support Vector Machine (SVM) Results")
            model = SVC(C=C, kernel=kernel, gamma=gamma)
            model.fit(x_train, y_train)
            accuracy = model.score(x_test, y_test)
            y_pred = model.predict(x_test)
            st.write("Accuracy: ", accuracy.round(2))
            st.write("Precision: ", precision_score(y_test, y_pred, labels=class_names).round(2))
            st.write("Recall: ", recall_score(y_test, y_pred, labels=class_names).round(2))
            utils.plot_metrics(metrics, model, x_test, y_test, class_names)


    if classifier == 'Logistic Regression':
        st.sidebar.subheader("Model Hyperparameters")
        C = st.sidebar.number_input("C (Regularization parameter)", 0.01, 10.0, step=0.01, key='Lr')
        max_iter = st.sidebar.slider("Maximum no. of iterations", 100, 500, key='max_iter')

        metrics = st.sidebar.multiselect("What matrix to plot?", ("Confusion Matrix", "ROC Curve",
                                                                  "Precision-Recall Curve"))

        if st.sidebar.button("Classify", key="classify"):
            st.subheader("Logistic Regression Results")
            model = LogisticRegression(C=C, max_iter=max_iter)
            model.fit(x_train, y_train)
            accuracy = model.score(x_test, y_test)
            y_pred = model.predict(x_test)
            st.write("Accuracy: ", accuracy.round(2))
            st.write("Precision: ", precision_score(y_test, y_pred, labels=class_names).round(2))
            st.write("Recall: ", recall_score(y_test, y_pred, labels=class_names).round(2))
            utils.plot_metrics(metrics, model, x_test, y_test, class_names)


    if classifier == 'Random Forest Classification':
        st.sidebar.subheader("Model Hyperparameters")
        n_estimators = st.sidebar.number_input("This is the number of trees in the forest", 100, 5000, step=10,
                                               key='n_estimators')
        max_depth = st.sidebar.number_input("The maximum depth of the tree", 1, 100, step=2, key='max_depth')
        bootstrap = st.sidebar.radio("Bootstrap samples when building trees", ("True", "False"), key='bootstrap')
        metrics = st.sidebar.multiselect("What matrix to plot?", ("Confusion Matrix", "ROC Curve",
                                                                  "Precision-Recall Curve"))

        if st.sidebar.button("Classify", key="classify"):
            st.subheader("Random Forest Results")
            model = RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth, bootstrap=bootstrap, n_jobs=-1)
            model.fit(x_train, y_train)
            accuracy = model.score(x_test, y_test)
            y_pred = model.predict(x_test)
            st.write("Accuracy: ", accuracy.round(2))
            st.write("Precision: ", precision_score(y_test, y_pred, labels=class_names).round(2))
            st.write("Recall: ", recall_score(y_test, y_pred, labels=class_names).round(2))
            utils.plot_metrics(metrics, model, x_test, y_test, class_names)


    if st.sidebar.checkbox("Show raw data", False):
        st.subheader("Mushroom Data Set (Classification)")
        st.write(df)


if __name__ == '__main__':
    main()