Automated_Data_Exploration/Code at main · nzaki02/Automated_Data_Exploration · 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
101
import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from pandas_profiling import ProfileReport
from streamlit_pandas_profiling import st_profile_report
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression

def main():
    st.title("Data Analysis App")

    menu = ["Data Automatic Exploration", "Data Classification", "Feature Analysis"]
    choice = st.sidebar.selectbox("Menu", menu)

    if choice == "Data Automatic Exploration":
        st.subheader("Automated Data Exploration")

        file = st.file_uploader("Upload a dataset", type=["csv", "xlsx"])
        if file is not None:
            st.subheader("Dataset")
            data = pd.read_csv(file)
            st.dataframe(data)

            profile = ProfileReport(data, explorative=True)
            st.header("Automated Data Report")
            st_profile_report(profile)

    elif choice == "Data Classification":
        st.subheader("Data Classification")

        file = st.file_uploader("Upload a dataset", type=["csv", "xlsx"])
        if file is not None:
            st.subheader("Dataset")
            data = pd.read_csv(file)
            st.dataframe(data)

            # Assume last column is target
            X = data.iloc[:, :-1]
            y = data.iloc[:, -1]

            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

            st.subheader("Classification Results")

            if st.button("Classify"):
                classifiers = [RandomForestClassifier(), SVC(), LogisticRegression()]
                classifier_names = ["Random Forest", "Support Vector Classifier", "Logistic Regression"]

                accuracies = {}

                for clf, clf_name in zip(classifiers, classifier_names):
                    clf.fit(X_train, y_train)
                    y_pred = clf.predict(X_test)
                    accuracies[clf_name] = accuracy_score(y_test, y_pred)
                    conf_mat = confusion_matrix(y_test, y_pred)

                    st.write(f"{clf_name} accuracy: ", accuracies[clf_name])

                    st.write(f"{clf_name} confusion matrix:")
                    fig, ax = plt.subplots()
                    sns.heatmap(conf_mat, annot=True, fmt='d', ax=ax)
                    ax.set_xlabel('Predicted')
                    ax.set_ylabel('Actual')
                    ax.set_title(f"{clf_name} Confusion Matrix")
                    st.pyplot(fig)

    elif choice == "Feature Analysis":
        st.subheader("Feature Analysis")

        file = st.file_uploader("Upload a dataset", type=["csv", "xlsx"])
        if file is not None:
            st.subheader("Dataset")
            data = pd.read_csv(file)
            st.dataframe(data)

            # Assume last column is target
            X = data.iloc[:, :-1]
            y = data.iloc[:, -1]

            if st.button("Feature Analysis"):
                st.subheader("Feature Analysis Results")
                st.write("Correlation Matrix:")
                st.dataframe(data.corr())

                st.write("Feature Importance:")
                model = RandomForestClassifier()
                model.fit(X, y)
                importances = pd.DataFrame({'feature':X.columns, 'importance':model.feature_importances_})
                fig = plt.figure()
                plt.barh(importances['feature'], importances['importance'])
                plt.xlabel("Importance")
                plt.ylabel("Feature")
                plt.title("Feature importances")
                st.pyplot(fig)

if __name__ == "__main__":
    main()