Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from utils import FraudDetectionAnalysis, BivariateAnalysis, GenderAnalysis | |
| st.title('Data Analysis') | |
| analysis = FraudDetectionAnalysis() | |
| bivariate = BivariateAnalysis() | |
| gender_analytics = GenderAnalysis() | |
| st.markdown("#### Categories") | |
| st.caption('It appears that most number of transactions in the dataset fall under the `gas_transport` category and the least fall under the `travel` category. When it comes to fraudulent transactions the least is observed under the `travel` category, while the majority are under the category `shopping_net` &`grocery_net`.') | |
| category, fraud_in_category = st.columns(2) | |
| with category: | |
| st.altair_chart( | |
| analysis.plot_univariate( | |
| key='Category', field="Transactions", title="All Transactions"), | |
| use_container_width=True) | |
| with fraud_in_category: | |
| st.altair_chart( | |
| analysis.plot_univariate( | |
| key='Category', field='Fraud', title="Fraudulent Transaction"), | |
| use_container_width=True) | |
| st.markdown("#### Gender") | |
| st.caption( | |
| "We can clearly see that the majority of transactions in the dataset are made by females.") | |
| st.altair_chart( | |
| analysis.plot_univariate( | |
| key='Gender', field="Transactions", title="Count"), | |
| use_container_width=True) | |
| st.caption( | |
| 'Fraudulent Transaction across different categories | Gender-wise analysis') | |
| st.bar_chart(data=gender_analytics.data['category_gender'], x='category') | |
| # heatmap | |
| st.caption( | |
| "Majority of frauds are observed under the category `shopping_net` & `grocery_pos`") | |
| st.pyplot( | |
| fig=gender_analytics.plot_heatmap( | |
| key='category_gender_heatmap', xlabel="Category" | |
| ), | |
| use_container_width=True) | |
| # 'age_group_and_gender_heatmap' | |
| st.markdown(''' | |
| * Majority of the fraudulent transactions are made by people belonging to the `age group 40 to 60` | |
| * Fraudulent Transactions recorded among the `age-group 80+` could be **identity theft** | |
| ''') | |
| st.pyplot( | |
| fig=gender_analytics.plot_heatmap( | |
| key='age_group_and_gender_heatmap', xlabel="Age Groups in the Dataset", rotation=0 | |
| ), | |
| use_container_width=True) | |
| st.markdown("#### Month of an year") | |
| st.caption( | |
| "Majority of transactions in the dataset are made in December and most of them occur during the Weekend.") | |
| month, fraud_in_month = st.columns(2) | |
| with month: | |
| st.altair_chart( | |
| analysis.plot_univariate( | |
| key='Month', field="Transactions", title="All Transactions"), | |
| use_container_width=True) | |
| with fraud_in_month: | |
| st.altair_chart( | |
| analysis.plot_univariate( | |
| key='Month', field="Fraud", title="Fraudulent Transaction"), | |
| use_container_width=True) | |
| st.markdown("#### Day of Week") | |
| day, fraud_in_day = st.columns(2) | |
| with day: | |
| st.altair_chart( | |
| analysis.pie_chart( | |
| key='Day of Week', field="Transactions", title="Transactions"), | |
| use_container_width=True) | |
| with fraud_in_day: | |
| st.altair_chart( | |
| analysis.pie_chart( | |
| key='Day of Week', field="Fraud", title="Fraudulent Transaction"), | |
| use_container_width=True) | |
| st.markdown('#### Bivariate Analysis') | |
| st.markdown(""" | |
| * Generally, people within the 40-60 years age group have done more fraudulent transactions | |
| * Transactions made within the distance range 50 - 100 KM are the most in the dataset. | |
| * Most of the Fraudulent transactions are recorded late at night. | |
| """) | |
| with st.spinner("📊...."): | |
| feature, display = st.columns(2) | |
| with feature: | |
| bivariate_feature = st.selectbox( | |
| label="Bivariate Analysis | Select the feature", | |
| options=["Age Group", "Transaction Hour", "Distance range in KM"] | |
| ) | |
| with display: | |
| y_axis = st.selectbox( | |
| label="Transaction", | |
| options=['Fraudulent Transaction', 'Fair Transaction', 'Total Transaction']) | |
| st.bar_chart(data=bivariate.get_data(bivariate_feature), | |
| x=bivariate_feature, y=y_axis) | |