Upload folder using huggingface_hub

app.py

@@ -41,7 +41,7 @@ if page == "Introduction":
         This application provides insights into Kiva loans data. 
         You can explore the distribution of funded amounts, 
         analyze top values by selected variables, and visualize 
-        relationships between funded amounts and various factors.
+        relationships between funded amounts and various factors such as Countries and Sectors that the loans were funded.
     """)
 
 # Data Overview Page
@@ -61,7 +61,7 @@ elif page == "Data Overview":
         title='Distribution of Funded Amounts'
     )
     st.altair_chart(chart, use_container_width=True)
-    st.write("This chart shows the distribution of funded amounts for Kiva loans. The x-axis represents the funded amount, while the y-axis shows the count of loans that fall within each bin.")
+    st.write("This chart shows the distribution of funded amounts for Kiva loans. The x-axis represents the funded amount, while the y-axis shows the count of loans that fall within each bin. As you can see most of the loans are low valued with most of them being in the range of 100 and 500")
 
 # Page 3: Top Values by Selected Variable
 elif page == "Top Values by Selected Variable":
@@ -72,7 +72,7 @@ elif page == "Top Values by Selected Variable":
 
     # Slider to select the number of top values to display
     num_columns = st.slider(
-        "Select Number of Columns to Display",
+        "Select Number of Columns to Display on the Chart",
         min_value=5,
         max_value=50,
         value=10,  # default value
@@ -84,17 +84,17 @@ elif page == "Top Values by Selected Variable":
         top_values = df_kiva_loans_cleaned.groupby('country')['funded_amount'].agg(['sum', 'count']).nlargest(num_columns, 'sum').reset_index()
         x_column = 'country'
         count_column = 'count'
-        description = f"This chart displays the top {num_columns} countries by total funded amount. The blue bars represent the total funded amount, while the red line indicates the count of loans."
+        description = f"This chart displays the top {num_columns} countries by total funded amount. The blue bars represent the total funded amount, while the red line indicates the count of loans. In general Phillipines is the country with the most loans followed by Kenya and El Salvador."
     elif plot_type == 'repayment_interval':
         top_values = df_kiva_loans_cleaned.groupby('repayment_interval')['funded_amount'].agg(['sum', 'count']).nlargest(num_columns, 'sum').reset_index()
         x_column = 'repayment_interval'
         count_column = 'count'
-        description = f"This chart shows the top {num_columns} repayment intervals by total funded amount. The blue bars represent the total funded amount, while the red line indicates the count of loans."
+        description = f"This chart shows the top {num_columns} repayment intervals by total funded amount. The blue bars represent the total funded amount, while the red line indicates the count of loans. Most of the loans are funded with a monthly repayment interval, where the bullet repayment is an unsusal choice"
     else:  # sector
         top_values = df_kiva_loans_cleaned.groupby('sector')['funded_amount'].agg(['sum', 'count']).nlargest(num_columns, 'sum').reset_index()
         x_column = 'sector'
         count_column = 'count'
-        description = f"This chart illustrates the top {num_columns} sectors by total funded amount. The blue bars represent the total funded amount, while the red line indicates the count of loans."
+        description = f"This chart illustrates the top {num_columns} sectors by total funded amount. The blue bars represent the total funded amount, while the red line indicates the count of loans. Most loans are funded to the Aggriculture Sector with Food and Retail completing the first three. Looks like that if the sector of the business is close to Primary production or its Basic Necessities(food) "
 
     # Display description
     st.write(description)
@@ -140,17 +140,19 @@ elif page == "Top Values by Selected Variable":
     if plot_type != 'repayment_interval':
         top_values_sorted = df_kiva_loans_cleaned.groupby(plot_type)['funded_amount'].agg('sum').nlargest(num_columns).index
         sns.boxplot(x=plot_type, y='funded_amount', data=filtered_df_boxplot, order=top_values_sorted, ax=ax)
+        st.write(f"This boxplot shows the distribution of funded amounts for the top {num_columns} {plot_type.replace('_', ' ')}. It provides insights into the spread and outliers of funded amounts.")
     else:
         sns.boxplot(x=plot_type, y='funded_amount', data=filtered_df_boxplot, ax=ax)
+        st.write(f"This boxplot shows the distribution of funded amounts for the top {num_columns} {plot_type.replace('_', ' ')}. It provides insights into the spread and outliers of funded amounts.")
 
     plt.title('Funded Amount by Selected Variable')
     plt.xlabel(plot_type)
     plt.ylabel('Funded Amount')
-    plt.xticks(rotation=45)
+    plt.xticks(rotation=90)
     st.pyplot(fig)
 
     # Display description for boxplot
-    st.write(f"This boxplot shows the distribution of funded amounts for the top {num_columns} {plot_type.replace('_', ' ')}. It provides insights into the spread and outliers of funded amounts.")
+    
 
 # Page 4: Other Plots
 elif page == "Repayment Interval by Selected Variable":
@@ -172,11 +174,11 @@ elif page == "Repayment Interval by Selected Variable":
     if plot_var == 'sector':
         top_values_plot = df_kiva_loans_cleaned.groupby('sector')['funded_amount'].agg('count').nlargest(num_top_values).index
         filtered_df_plot = df_kiva_loans_cleaned[df_kiva_loans_cleaned['sector'].isin(top_values_plot)]
-        description = f"This countplot shows the distribution of repayment intervals for the top {num_top_values} sectors based on the number of loans."
+        description = f"This countplot shows the distribution of repayment intervals for the top {num_top_values} sectors based on the number of loans. In terms of sectors Agriculture got the most monthly repayment loans followed by food. Also a lot of irregulars were in the Food, Retail and Agriculture sectors, which again confirms that loans for first necessities are given more easily. "
     elif plot_var == 'country':
         top_values_plot = df_kiva_loans_cleaned.groupby('country')['funded_amount'].agg('count').nlargest(num_top_values).index
         filtered_df_plot = df_kiva_loans_cleaned[df_kiva_loans_cleaned['country'].isin(top_values_plot)]
-        description = f"This countplot illustrates the distribution of repayment intervals for the top {num_top_values} countries based on the number of loans."
+        description = f"This countplot illustrates the distribution of repayment intervals for the top {num_top_values} countries based on the number of loans. In terms of countries the Phillipines had a great number of Irregular loans."
 
     # Display description
     st.write(description)
@@ -211,10 +213,10 @@ elif page == "Country Comparison Deepdive":
     st.subheader("Country Comparison Deepdive")
 
     # Multi-select for countries
-    selected_countries = st.multiselect("Select Countries to Compare", options=df_kiva_loans_cleaned['country'].unique())
+    selected_countries = st.multiselect("Select Countries to Compare(Please select one or more)", options=df_kiva_loans_cleaned['country'].unique())
 
     # Option to choose between count or sum of funded amounts
-    aggregation_option = st.radio("Select Aggregation Type:", ("Count", "Sum"))
+    aggregation_option = st.radio("Select Aggregation Type:", ("Count of Loans", "Summary of Funded Amount"))
 
     if selected_countries:
         # Filter the data based on selected countries
@@ -226,10 +228,12 @@ elif page == "Country Comparison Deepdive":
             sector_summary = filtered_data.groupby(['country', 'sector']).agg(
                 total_funded_amount=('funded_amount', 'sum')
             ).reset_index()
+            st.write("This graph shows the total funded amount in each Sector for the selected Countries by the user.")
         else:  # Count
             sector_summary = filtered_data.groupby(['country', 'sector']).agg(
                 total_funded_amount=('funded_amount', 'count')
             ).reset_index()
+            st.write("This graph shows the number of loans in each Sector for the selected Countries by the user.")
 
         fig, ax = plt.subplots(figsize=(12, 6))
         sns.barplot(x='sector', y='total_funded_amount', hue='country', data=sector_summary, ax=ax)
@@ -241,14 +245,16 @@ elif page == "Country Comparison Deepdive":
 
         # Create a combined bar plot for repayment summary
         st.subheader("Total Funded Amounts by Repayment Interval for Selected Countries")
-        if aggregation_option == "Sum":
+        if aggregation_option == "Summary of Funded Amount":
             repayment_summary = filtered_data.groupby(['country', 'repayment_interval']).agg(
                 total_funded_amount=('funded_amount', 'sum')
             ).reset_index()
+            st.write("This graph shows the total funded amount in each Repayment interval for the selected Countries by the user.")
         else:  # Count
             repayment_summary = filtered_data.groupby(['country', 'repayment_interval']).agg(
                 total_funded_amount=('funded_amount', 'count')
             ).reset_index()
+            st.write("This graph shows the number of loans in each Repayment interval for the selected Countries by the user.")
 
         fig, ax = plt.subplots(figsize=(12, 6))
         sns.barplot(x='repayment_interval', y='total_funded_amount', hue='country', data=repayment_summary, ax=ax)
@@ -258,17 +264,17 @@ elif page == "Country Comparison Deepdive":
         plt.xticks(rotation=45)
         st.pyplot(fig)
     else:
-        st.write("Please select one or more countries to compare.")
+        st.write("Please select one or more countries to compare from the dropdown above.")
 
 # Page 6: Sector Comparison
 elif page == "Sector Comparison Deepdive":
     st.subheader("Sector Comparison Deepdive")
 
     # Multi-select for sectors
-    selected_sectors = st.multiselect("Select Sectors to Compare", options=df_kiva_loans_cleaned['sector'].unique())
+    selected_sectors = st.multiselect("Select Sectors to Compare (Please select one or more)", options=df_kiva_loans_cleaned['sector'].unique())
 
     # Option to choose between count or sum of funded amounts
-    aggregation_option = st.radio("Select Aggregation Type:", ("Count", "Sum"))
+    aggregation_option = st.radio("Select Aggregation Type:", ("Count of Loans", "Summmary of Funded Amount"))
 
     if selected_sectors:
         # Filter the data based on selected sectors
@@ -276,14 +282,16 @@ elif page == "Sector Comparison Deepdive":
 
         # Create a combined bar plot for sector summary by country
         st.subheader("Total Funded Amounts by Country for Selected Sectors")
-        if aggregation_option == "Sum":
+        if aggregation_option == "Summary of Funded Amount":
             country_summary = filtered_data.groupby(['country', 'sector']).agg(
                 total_funded_amount=('funded_amount', 'sum')
             ).reset_index()
+            st.write("This graph shows the total funded amount in each Country, for the selected Sectors by the user.")
         else:  # Count
             country_summary = filtered_data.groupby(['country', 'sector']).agg(
                 total_funded_amount=('funded_amount', 'count')
             ).reset_index()
+            st.write("This graph shows the number of loans in each Country, for the selected Sectors by the user.")
 
         fig, ax = plt.subplots(figsize=(12, 6))
         sns.barplot(x='country', y='total_funded_amount', hue='sector', data=country_summary, ax=ax)
@@ -300,10 +308,12 @@ elif page == "Sector Comparison Deepdive":
             repayment_summary = filtered_data.groupby(['repayment_interval', 'sector']).agg(
                 total_funded_amount=('funded_amount', 'sum')
             ).reset_index()
+            st.write("This graph shows the funded amount in each Repayment interval for the selected Sectors  by the user.")
         else:  # Count
             repayment_summary = filtered_data.groupby(['repayment_interval', 'sector']).agg(
                 total_funded_amount=('funded_amount', 'count')
             ).reset_index()
+            st.write("This graph shows the number of loans in each Repayment interval for the selected Sectors by the user.")
 
         fig, ax = plt.subplots(figsize=(12, 6))
         sns.barplot(x='repayment_interval', y='total_funded_amount', hue='sector', data=repayment_summary, ax=ax)
@@ -314,4 +324,5 @@ elif page == "Sector Comparison Deepdive":
         plt.xticks(rotation=90)
         st.pyplot(fig)
     else:
-        st.write("Please select one or more sectors to compare.")
+        st.write("Please select one or more countries to compare from the dropdown above.")
+