Upload folder using huggingface_hub

app.py

@@ -6,7 +6,6 @@ import matplotlib.pyplot as plt
 from scipy.stats import zscore
 import seaborn as sns
 
-st.title('my shitty app ')
 
 file_path= 'kiva_loans.csv'
 
@@ -24,18 +23,55 @@ z_scores = zscore(df_kiva_loans['funded_amount'])
 df_kiva_loans['outlier_funded_amount'] = (z_scores > 3) | (z_scores < -3)
 df_kiva_loans_cleaned = df_kiva_loans[~df_kiva_loans['outlier_funded_amount']]
 
-#Grouping by 'repayment interval' and calculating  mean,sum and max for funded amount and loan amount.
+st.title('BDS24_Weekly_Assignment_Week 2| Tryfonas Karmiris')
+# Sidebar selection for the type of plot
+plot_type = st.sidebar.selectbox("Select Variable to Display", ['country', 'repayment_interval', 'sector'])
 
-selected = st.sidebar.selectbox("Select Variable of Interest", ['country', 'sector', 'repayment_interval'])
-selected2 = st.sidebar.selectbox("Select Variable of Interest", ['funded_amount', 'count'])
+# Slider to select the number of top values to display
+num_columns = st.sidebar.slider(
+    "Select Number of Columns to Display",
+    min_value=5,
+    max_value=20,
+    value=10,  # default value
+    step=1
+)
 
-if selected2 == 'count':
-    result = df_kiva_loans.groupby(selected).size().reset_index(name='count')
-    result = result.sort_values(by='count', ascending=False)
-else:
-    result = df_kiva_loans.groupby(selected)[selected2].sum().reset_index()
-    result = result.sort_values(by=selected2, ascending=False)
+# Select the top values based on the selected variable and number of columns
+if plot_type == 'country':
+    top_values = df_kiva_loans.groupby('country')['funded_amount'].agg(['sum', 'count']).nlargest(num_columns, 'sum').reset_index()
+    x_column = 'country'
+    count_column = 'count'
+elif plot_type == 'repayment_interval':
+    top_values = df_kiva_loans.groupby('repayment_interval')['funded_amount'].agg(['sum', 'count']).nlargest(num_columns, 'sum').reset_index()
+    x_column = 'repayment_interval'
+    count_column = 'count'
+else:  # sector
+    top_values = df_kiva_loans.groupby('sector')['funded_amount'].agg(['sum', 'count']).nlargest(num_columns, 'sum').reset_index()
+    x_column = 'sector'
+    count_column = 'count'
 
-st.title("Aggregated Data")
-st.table(result)
+# Create a bar plot with dual axes
+fig, ax1 = plt.subplots(figsize=(12, 9))
+plt.xticks(rotation=90)
 
+# Bar plot for funded_amount
+color = 'tab:blue'
+ax1.set_xlabel(x_column.replace("_", " ").title())
+ax1.set_ylabel('Funded Amount', color=color)
+ax1.bar(top_values[x_column], top_values['sum'], color=color, alpha=0.6, label='Funded Amount')
+ax1.tick_params(axis='y', labelcolor=color)
+
+# Create a second y-axis for count
+ax2 = ax1.twinx()
+color = 'tab:red'
+ax2.set_ylabel('Count', color=color)
+ax2.plot(top_values[x_column], top_values[count_column], color=color, marker='o', linestyle='-', linewidth=2, label='Count')
+ax2.tick_params(axis='y', labelcolor=color)
+
+# Add titles and labels
+plt.title(f'Top {num_columns} by {plot_type.replace("_", " ").title()}')
+fig.tight_layout()
+
+
+# Display the plot in Streamlit
+st.pyplot(fig)