Update app.py

app.py

@@ -69,45 +69,64 @@ st.write("Predictions have been logged. Check your logs for details.")
 """
 import streamlit as st
 import pandas as pd
-from transformers import pipeline
-from sklearn.metrics import accuracy_score, precision_recall_fscore_support, confusion_matrix
 import seaborn as sns
 import matplotlib.pyplot as plt
+from sklearn.metrics import accuracy_score, precision_recall_fscore_support, confusion_matrix
+
 
 # Load data
 data = pd.read_excel("ResponseOpenPredicted.xlsx")
 st.title("Resume-based Personality Prediction by Serikov Ayanbek")
 
-# Calculate metrics
+# Function to calculate metrics
 def calculate_metrics(true_labels, predicted_labels):
     accuracy = accuracy_score(true_labels, predicted_labels)
     precision, recall, f1_score, _ = precision_recall_fscore_support(true_labels, predicted_labels, average='weighted')
     return accuracy, precision, recall, f1_score
 
+# Metrics Calculation
 accuracy_f, precision_f, recall_f, f1_score_f = calculate_metrics(data['True_label'], data['Predicted_F'])
 accuracy_m, precision_m, recall_m, f1_score_m = calculate_metrics(data['True_label'], data['Predicted_M'])
 
-# Confusion matrices visualization
+# Plotting function for confusion matrices
+def plot_confusion_matrix(conf_matrix, title):
+    fig, ax = plt.subplots()
+    sns.heatmap(conf_matrix, annot=True, fmt="d", cmap="Blues", ax=ax)
+    plt.title(title)
+    plt.xlabel('Predicted Labels')
+    plt.ylabel('True Labels')
+    st.pyplot(fig)
+
+# Plotting function for distribution of predictions
+def plot_predictions_distribution(data, column, title):
+    fig, ax = plt.subplots()
+    sns.countplot(x=column, data=data, palette="viridis")
+    plt.title(title)
+    plt.xlabel('Predicted Labels')
+    plt.ylabel('Count')
+    st.pyplot(fig)
+
+# Streamlit app structure
+st.title('Model Performance Evaluation')
+
+st.subheader('Performance Metrics')
+st.write(f"Accuracy for Predicted_F: {accuracy_f:.2%}")
+st.write(f"Precision for Predicted_F: {precision_f:.2%}")
+st.write(f"Recall for Predicted_F: {recall_f:.2%}")
+st.write(f"F1-Score for Predicted_F: {f1_score_f:.2%}")
+st.write(f"Accuracy for Predicted_M: {accuracy_m:.2%}")
+st.write(f"Precision for Predicted_M: {precision_m:.2%}")
+st.write(f"Recall for Predicted_M: {recall_m:.2%}")
+st.write(f"F1-Score for Predicted_M: {f1_score_m:.2%}")
+
+st.subheader('Confusion Matrices')
 conf_matrix_f = confusion_matrix(data['True_label'], data['Predicted_F'])
 conf_matrix_m = confusion_matrix(data['True_label'], data['Predicted_M'])
-
-fig, ax = plt.subplots(1, 2, figsize=(12, 6))
-sns.heatmap(conf_matrix_f, annot=True, fmt="d", cmap="Blues", ax=ax[0])
-ax[0].set_title('Confusion Matrix for Predicted_F')
-sns.heatmap(conf_matrix_m, annot=True, fmt="d", cmap="Purples", ax=ax[1])
-ax[1].set_title('Confusion Matrix for Predicted_M')
-
-# Distribution of prediction results
-fig, ax = plt.subplots(1, 2, figsize=(12, 6))
-data['Predicted_F'].value_counts().plot(kind='bar', ax=ax[0], color='blue')
-ax[0].set_title('Distribution of Predictions for Female Inputs')
-ax[0].set_xlabel('Predicted Labels')
-ax[0].set_ylabel('Frequency')
-
-data['Predicted_M'].value_counts().plot(kind='bar', ax=ax[1], color='purple')
-ax[1].set_title('Distribution of Predictions for Male Inputs')
-ax[1].set_xlabel('Predicted Labels')
-ax[1].set_ylabel('Frequency')
-
-plt.tight_layout()
-plt.show()
+plot_confusion_matrix(conf_matrix_f, 'Confusion Matrix for Predicted_F')
+plot_confusion_matrix(conf_matrix_m, 'Confusion Matrix for Predicted_M')
+
+st.subheader('Distribution of Prediction Results')
+st.write("Distribution for Predicted_F")
+plot_predictions_distribution(data, 'Predicted_F', 'Distribution of Predictions for Female Demographic')
+st.write("Distribution for Predicted_M")
+plot_predictions_distribution(data, 'Predicted_M', 'Distribution of Predictions for Male Demographic')