Update eda.py

eda.py

@@ -4,4 +4,173 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 
 def app():
-    st.title('Exploratory Data Analysis')
+    st.title('Exploratory Data Analysis')
+    
+    # Load Data
+    df = pd.read_csv('../Transactions Data.csv')
+
+    # Data Summary
+    st.header('Data Summary')
+    st.write(df.describe().T)
+
+    st.divider()
+
+    # Univariate Exploration
+    st.header('Univariate Analysis')
+    
+    # 1
+    st.subheader('Distribution of Transactions Types')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['type'], bins=20, ax=ax)
+    plt.xlabel('Transaction Types')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of Transaction Types')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 2
+    st.subheader('Distribution of Balance Amount')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['amount'], bins=20, ax=ax)
+    plt.xlabel('Amount')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of Balance Amount')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 3
+    st.subheader('Distribution of Old Balance Origin')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['oldbalanceOrg'], bins=20, ax=ax)
+    plt.xlabel('Old Balance Origin')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of Old Balance Origin')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+
+    # 4
+    st.subheader('Distribution of New Balance Origin')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['newbalanceOrig'], bins=20, ax=ax)
+    plt.xlabel('New Balance Origin')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of New Balance Origin')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 5 
+    st.subheader('Distribution of Old Balance Destination')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['oldbalanceDest'], bins=20, ax=ax)
+    plt.xlabel('Old Balance Origin')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of Old Balance Destination')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    
+    # 5 
+    st.subheader('Distribution of New Balance Destination')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['newbalanceDest'], bins=20, ax=ax)
+    plt.xlabel('New Balance Origin')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of New Balance Destination')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 6
+    st.subheader('Distribution of Flagged Fraud')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['isFlaggedFraud'], bins=20, ax=ax)
+    plt.xlabel('Is Flagged Fraud')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of Flagged Fraud')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 7
+    st.subheader('Distribution of Fraud')
+    # Plotting
+    fig, ax = plt.subplots()
+    sns.histplot(df['isFraud'], bins=20, ax=ax)
+    plt.xlabel('Is Fraud')
+    plt.ylabel('Frequency')
+    plt.title('Distribution of Fraud')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+
+    st.divider()
+
+    # Bivariate analysis
+    st.header('Bivariate Analysis')
+
+    # 1
+    st.subheader('Distribution of Amout Balance per Transaction Types')
+    fig, ax = plt.subplots()
+    sns.boxplot(x=df['amount'], y=df['type'], ax=ax)
+    plt.xlabel('Amount')
+    plt.ylabel('Transaction Types')
+    plt.title('Transaction Types vs Amount Balance')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 2
+    st.subheader('Distribution of Old Balance Origin per Transaction Types')
+    fig, ax = plt.subplots()
+    sns.boxplot(x=df['oldbalanceOrg'], y=df['type'], ax=ax)
+    plt.xlabel('Old Balance Origin')
+    plt.ylabel('Transaction Types')
+    plt.title('Transaction Types vs Old Balance Origin')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+    
+    # 3
+    st.subheader('Distribution of New Balance Origin per Transaction Types')
+    fig, ax = plt.subplots()
+    sns.boxplot(x=df['newbalanceOrig'], y=df['type'], ax=ax)
+    plt.xlabel('New Balance Origin')
+    plt.ylabel('Transaction Types')
+    plt.title('Transaction Types vs Old Balance Origin')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+
+    # 4
+    st.subheader('Distribution of Old Balance Destination per Transaction Types')
+    fig, ax = plt.subplots()
+    sns.boxplot(x=df['oldbalanceDest'], y=df['type'], ax=ax)
+    plt.xlabel('Old Balance Destination')
+    plt.ylabel('Transaction Types')
+    plt.title('Transaction Types vs Old Balance Destination')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')
+
+    # 5
+    st.subheader('Distribution of New Balance Destination per Transaction Types')
+    fig, ax = plt.subplots()
+    sns.boxplot(x=df['newbalanceDest'], y=df['type'], ax=ax)
+    plt.xlabel('New Balance Destination')
+    plt.ylabel('Transaction Types')
+    plt.title('Transaction Types vs New Balance Destination')
+    st.pyplot(fig)
+    st.write('bla bla bla')
+    st.write('')