Update Backend.py

Backend.py

@@ -1,176 +1,176 @@
-import matplotlib.pyplot as plt
-from fpdf import FPDF
-from datetime import datetime
-from huggingfaceModel import generate_dropout_insights
-#rom ollamaModel import generate_dropout_insights
-import re
-import os
-
-def format_key(key):
-    """Format keys to be more readable by capitalizing and removing underscores."""
-    return key.replace("_", " ").title()
-
-def remove_unsupported_characters(text):
-    """Removes emojis and unsupported Unicode characters for PDF compatibility."""
-    return text.encode("ascii", "ignore").decode()
-
-def generate_pdf(input_data, dropout_risk, summary):
-    """Generates a structured, professional PDF report for dropout prediction results."""
-    
-    pdf = FPDF()
-    pdf.add_page()
-
-    # 🔹 Check if DejaVuSans font files exist
-    if os.path.exists("DejaVuSans.ttf") and os.path.exists("DejaVuSans-Bold.ttf") and os.path.exists("DejaVuSans-Oblique.ttf"):
-        font_name = "DejaVu"
-        pdf.add_font("DejaVu", "", "Dejavu/DejaVuSans.ttf", uni=True)
-        pdf.add_font("DejaVu", "B", "Dejavu/DejaVuSans-Bold.ttf", uni=True)
-        pdf.add_font("DejaVu", "I", "Dejavu/DejaVuSans-Oblique.ttf", uni=True)
-    else:
-        font_name = "Arial"  # Use default Arial if DejaVu fonts are missing
-    
-    # 🔹 Cover Page
-    pdf.set_font(font_name, "B", 20)
-    pdf.cell(200, 15, "AI-DRIVEN DROPOUT PREDICTION AND PREVENTION TOOL", ln=True, align="C")
-
-    pdf.set_font(font_name, "I", 12)
-    pdf.cell(200, 10, "Generated by: AI Dropout Predictor System", ln=True, align="C")
-    pdf.cell(200, 10, f"Date: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ln=True, align="C")
-
-    pdf.ln(20)
-    pdf.set_font(font_name, "B", 16)
-    pdf.cell(200, 10, "Confidential Report", ln=True, align="C")
-
-    pdf.ln(10)
-    pdf.set_font(font_name, "I", 12)
-    pdf.cell(200, 10, "This document contains confidential student information and predictive analysis.", ln=True, align="C")
-
-    pdf.add_page()
-
-    # 🔹 Student Information Section
-    pdf.set_font(font_name, "B", 14)
-    pdf.cell(200, 10, "Student Information", ln=True, align="L")
-    pdf.ln(5)
-
-    pdf.set_font(font_name, "", 12)
-    for key, value in input_data.items():
-        formatted_key = key.replace("_", " ").title()
-        pdf.cell(90, 8, f"{formatted_key}:", border=1, align="L")
-        pdf.cell(100, 8, str(value), border=1, align="L")
-        pdf.ln(8)
-
-    pdf.ln(10)
-    pdf.add_page()
-
-    # 🔹 Dropout Risk Score Section
-    pdf.set_font(font_name, "B", 14)
-    pdf.cell(200, 10, "Predicted Dropout Risk Score", ln=True, align="L")
-    pdf.ln(5)
-
-    pdf.set_font(font_name, "B", 16)
-    pdf.set_fill_color(240, 240, 240)
-    pdf.cell(200, 15, f" Dropout Risk Score: {dropout_risk}/10 ", ln=True, align="L", border=1, fill=True)
-
-    pdf.ln(10)
-
-    # 🔹 Dropout Prediction Graph
-    pdf.set_font(font_name, "B", 14)
-    pdf.cell(200, 10, "Dropout Risk Analysis Graph", ln=True, align="C")
-    pdf.ln(5)
-
-    if os.path.exists("dropout_plot.png"):
-        pdf.image("dropout_plot.png", x=50, w=100)
-    else:
-        pdf.cell(200, 10, "Graph Unavailable", ln=True, align="C")
-
-    pdf.ln(20)
-    pdf.add_page()
-
-    # 🔹 Summary Section
-    pdf.set_font(font_name, "B", 14)
-    pdf.cell(200, 10, "Summary of Student Data", ln=True, align="C")
-    pdf.ln(5)
-
-    pdf.set_font(font_name, "", 12)
-    cleaned_summary = remove_unsupported_characters(summary)
-    pdf.multi_cell(0, 7, cleaned_summary, align="L")
-
-    # 🔹 Disclaimer
-    pdf.set_y(-30)
-    pdf.set_font(font_name, "I", 10)
-    pdf.cell(200, 10, "Disclaimer:", ln=True, align="L")
-    pdf.multi_cell(0, 7, "This report is generated using predictive analysis. It does not guarantee actual dropout behavior but serves as a guideline for early intervention.", align="L")
-
-    # 🔹 Save PDF
-    pdf_filename = "Dropout_Report.pdf"
-    pdf.output(pdf_filename)
-
-    return pdf_filename
-
-def calculate_risk(value, thresholds, weights):
-    """Assigns a risk weight based on threshold conditions."""
-    for threshold, weight in zip(thresholds, weights):
-        if value <= threshold:
-            return weight
-    return weights[-1]
-
-def predict_dropout(**kwargs):
-    """Predicts dropout risk based on multiple risk factors."""
-    risk_factors = [
-        calculate_risk(1 if kwargs.get("special_lab") == "Non-Active" else 0, [0, 1], [-0.1, 0.5]),
-        calculate_risk(kwargs.get("attendance_percentage", 0), [50, 65, 75, 85], [1.0, 0.7, 0.4, -0.2]),
-        calculate_risk(kwargs.get("formative_assessment", 0), [30, 50, 70, 85], [1.0, 0.7, 0.4, -0.2]),
-        calculate_risk(kwargs.get("cgpa", 0), [5.0, 6.0, 7.0, 8.5], [1.0, 0.7, 0.4, -0.2]),
-        calculate_risk(kwargs.get("current_sgpa", 0), [5.0, 6.0, 7.0, 8.5], [1.0, 0.7, 0.4, -0.2]),
-        calculate_risk(kwargs.get("arrear_count", 0), [1, 3, 6, 10], [0.6, 0.8, 1.0, 1.3]),
-        calculate_risk(kwargs.get("full_stack_rank", 0), [300, 800, 1200, 1600], [-0.3, 0.1, 0.3, 0.6]),
-        calculate_risk(kwargs.get("ps_rank", 0), [1, 2, 4, 6], [0.8, 0.6, 0.4, -0.2]),
-        calculate_risk(kwargs.get("Overall_Skills_Acquired", 0), [1, 4, 8, 12], [0.8, 0.5, 0.3, -0.2]),
-        calculate_risk(kwargs.get("placement_fa", 0), [40, 60, 80, 95], [1.0, 0.7, 0.3, -0.2]),
-        calculate_risk(kwargs.get("interim_assessment_status", 0), [50, 70, 85, 95], [1.0, 0.7, 0.3, -0.2]),
-        calculate_risk(kwargs.get("training_assessment_status", 0), [50, 70, 85, 95], [1.0, 0.7, 0.3, -0.2]),
-        calculate_risk(kwargs.get("mock_assessment_status", 0), [30, 50, 70, 85], [1.0, 0.7, 0.3, -0.2]),
-        calculate_risk(kwargs.get("placement_cumulative", 0), [50, 70, 85, 95], [1.0, 0.7, 0.3, -0.2]),
-        calculate_risk(kwargs.get("placement_Attendence", 0), [50, 70, 85, 95], [1.0, 0.7, 0.3, -0.2]),
-        *(calculate_risk(kwargs.get(activity, 0), [0, 1, 3], [0.6, -0.2, -0.4]) for activity in [
-            "Technical_Competition", "Paper_Presentation", "Project_Competition", 
-            "Product_Development", "Patent", "Internship", "Online_Course"
-        ])
-    ]
-    print(risk_factors)
-
-    total_risk = min(10, max(0, sum(risk_factors)))
-    return total_risk, risk_factors
-
-def generate_plot(dropout_risk):
-    """Creates a bar plot for dropout risk."""
-    fig, ax = plt.subplots()
-    colors = ['green', 'lightgreen', 'yellow', 'orange', 'red']
-    labels = ['Very Low Risk', 'Low Risk', 'Moderate Risk', 'High Risk', 'Very High Risk']
-    index = min(int(dropout_risk // 2), 4)
-
-    ax.bar([labels[index]], [dropout_risk], color=colors[index])
-    ax.set_ylim(0, 10)
-    ax.set_ylabel('Dropout Risk Score')
-    ax.set_title('Dropout Risk Prediction')
-
-    plt.savefig("dropout_plot.png")  # Save before using in PDF
-    return fig
-
-def remove_emojis(text):
-    """Removes all emojis and unsupported Unicode characters from text."""
-    emoji_pattern = re.compile("[\U00010000-\U0010ffff]", flags=re.UNICODE)
-    return emoji_pattern.sub("", text)
-
-def process_and_generate_report(**input_values):
-
-    """Processes input values and generates risk prediction along with a report."""
-    
-    dropout_risk,risk_factor = predict_dropout(**input_values)
-    insights = generate_dropout_insights(input_values,risk_factor)
-    cleaned_insights = remove_emojis(insights)
-    fig = generate_plot(dropout_risk)
-    pdf_filename = generate_pdf(input_values, dropout_risk, cleaned_insights)
-    
-
+import matplotlib.pyplot as plt
+from fpdf import FPDF
+from datetime import datetime
+from huggingfaceModel import generate_dropout_insights
+#rom ollamaModel import generate_dropout_insights
+import re
+import os
+
+def format_key(key):
+    """Format keys to be more readable by capitalizing and removing underscores."""
+    return key.replace("_", " ").title()
+
+def remove_unsupported_characters(text):
+    """Removes emojis and unsupported Unicode characters for PDF compatibility."""
+    return text.encode("ascii", "ignore").decode()
+
+def generate_pdf(input_data, dropout_risk, summary):
+    """Generates a structured, professional PDF report for dropout prediction results."""
+    
+    pdf = FPDF()
+    pdf.add_page()
+
+    # 🔹 Check if DejaVuSans font files exist
+    if os.path.exists("DejaVuSans.ttf") and os.path.exists("DejaVuSans-Bold.ttf") and os.path.exists("DejaVuSans-Oblique.ttf"):
+        font_name = "DejaVu"
+        pdf.add_font("DejaVu", "", "Dejavu/DejaVuSans.ttf", uni=True)
+        pdf.add_font("DejaVu", "B", "Dejavu/DejaVuSans-Bold.ttf", uni=True)
+        pdf.add_font("DejaVu", "I", "Dejavu/DejaVuSans-Oblique.ttf", uni=True)
+    else:
+        font_name = "Arial"  # Use default Arial if DejaVu fonts are missing
+    
+    # 🔹 Cover Page
+    pdf.set_font(font_name, "B", 20)
+    pdf.cell(200, 15, "AI-DRIVEN DROPOUT PREDICTION AND PREVENTION TOOL", ln=True, align="C")
+
+    pdf.set_font(font_name, "I", 12)
+    pdf.cell(200, 10, "Generated by: AI Dropout Predictor System", ln=True, align="C")
+    pdf.cell(200, 10, f"Date: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ln=True, align="C")
+
+    pdf.ln(20)
+    pdf.set_font(font_name, "B", 16)
+    pdf.cell(200, 10, "Confidential Report", ln=True, align="C")
+
+    pdf.ln(10)
+    pdf.set_font(font_name, "I", 12)
+    pdf.cell(200, 10, "This document contains confidential student information and predictive analysis.", ln=True, align="C")
+
+    pdf.add_page()
+
+    # 🔹 Student Information Section
+    pdf.set_font(font_name, "B", 14)
+    pdf.cell(200, 10, "Student Information", ln=True, align="L")
+    pdf.ln(5)
+
+    pdf.set_font(font_name, "", 12)
+    for key, value in input_data.items():
+        formatted_key = key.replace("_", " ").title()
+        pdf.cell(90, 8, f"{formatted_key}:", border=1, align="L")
+        pdf.cell(100, 8, str(value), border=1, align="L")
+        pdf.ln(8)
+
+    pdf.ln(10)
+    pdf.add_page()
+
+    # 🔹 Dropout Risk Score Section
+    pdf.set_font(font_name, "B", 14)
+    pdf.cell(200, 10, "Predicted Dropout Risk Score", ln=True, align="L")
+    pdf.ln(5)
+
+    pdf.set_font(font_name, "B", 16)
+    pdf.set_fill_color(240, 240, 240)
+    pdf.cell(200, 15, f" Dropout Risk Score: {dropout_risk}/10 ", ln=True, align="L", border=1, fill=True)
+
+    pdf.ln(10)
+
+    # 🔹 Dropout Prediction Graph
+    pdf.set_font(font_name, "B", 14)
+    pdf.cell(200, 10, "Dropout Risk Analysis Graph", ln=True, align="C")
+    pdf.ln(5)
+
+    if os.path.exists("dropout_plot.png"):
+        pdf.image("dropout_plot.png", x=50, w=100)
+    else:
+        pdf.cell(200, 10, "Graph Unavailable", ln=True, align="C")
+
+    pdf.ln(20)
+    pdf.add_page()
+
+    # 🔹 Summary Section
+    pdf.set_font(font_name, "B", 14)
+    pdf.cell(200, 10, "Summary of Student Data", ln=True, align="C")
+    pdf.ln(5)
+
+    pdf.set_font(font_name, "", 12)
+    cleaned_summary = remove_unsupported_characters(summary)
+    pdf.multi_cell(0, 7, cleaned_summary, align="L")
+
+    # 🔹 Disclaimer
+    pdf.set_y(-30)
+    pdf.set_font(font_name, "I", 10)
+    pdf.cell(200, 10, "Disclaimer:", ln=True, align="L")
+    pdf.multi_cell(0, 7, "This report is generated using predictive analysis. It does not guarantee actual dropout behavior but serves as a guideline for early intervention.", align="L")
+
+    # 🔹 Save PDF
+    pdf_filename = "Dropout_Report.pdf"
+    pdf.output(pdf_filename)
+
+    return pdf_filename
+
+def calculate_risk(value, thresholds, weights):
+    """Assigns a risk weight based on threshold conditions."""
+    for threshold, weight in zip(thresholds, weights):
+        if value <= threshold:
+            return weight
+    return weights[-1]
+
+def predict_dropout(**kwargs):
+    """Predicts dropout risk based on multiple risk factors."""
+    risk_factors = [
+        calculate_risk(1 if kwargs.get("special_lab") == "Non-Active" else 0, [0, 1], [-0.1, 0.5]),
+        calculate_risk(kwargs.get("attendance_percentage", 0), [50, 65, 75, 85], [1.0, 0.7, 0.2, -0.2]),
+        calculate_risk(kwargs.get("formative_assessment", 0), [30, 50, 70, 85], [1.0, 0.7, 0.4, -0.2]),
+        calculate_risk(kwargs.get("cgpa", 0), [5.0, 6.0, 7.0, 8.5], [1.0, 0.7, 0.4, -0.2]),
+        calculate_risk(kwargs.get("current_sgpa", 0), [5.0, 6.0, 7.0, 8.5], [1.0, 0.7, 0.4, -0.2]),
+        calculate_risk(kwargs.get("arrear_count", 0), [1, 3, 6, 10], [0.6, 0.8, 1.0, 1.3]),
+        calculate_risk(kwargs.get("full_stack_rank", 0), [300, 800, 1200, 1600], [-0.3, -0.1, 0.3, 0.6]),
+        calculate_risk(kwargs.get("ps_rank", 0), [1, 2, 4, 6], [0.8, 0.6, -0.1, -0.2]),
+        calculate_risk(kwargs.get("Overall_Skills_Acquired", 0), [1, 4, 8, 12], [0.8, 0.5, -0.1, -0.2]),
+        calculate_risk(kwargs.get("placement_fa", 0), [40, 60, 80, 95], [1.0, 0.7, -0.1, -0.2]),
+        calculate_risk(kwargs.get("interim_assessment_status", 0), [50, 70, 85, 95], [1.0, 0.7, -0.1, -0.2]),
+        calculate_risk(kwargs.get("training_assessment_status", 0), [50, 70, 85, 95], [1.0, 0.7, -0.1, -0.2]),
+        calculate_risk(kwargs.get("mock_assessment_status", 0), [30, 50, 70, 85], [1.0, 0.7, 0.3, -0.2]),
+        calculate_risk(kwargs.get("placement_cumulative", 0), [50, 70, 85, 95], [1.0, 0.7, -0.1, -0.2]),
+        calculate_risk(kwargs.get("placement_Attendence", 0), [50, 70, 85, 95], [1.0, 0.7, -0.1, -0.2]),
+        *(calculate_risk(kwargs.get(activity, 0), [0, 1, 3], [0.1, -0.2, -0.4]) for activity in [
+            "Technical_Competition", "Paper_Presentation", "Project_Competition", 
+            "Product_Development", "Patent", "Internship", "Online_Course"
+        ])
+    ]
+    print(risk_factors)
+
+    total_risk = min(10, max(0, sum(risk_factors)))
+    return total_risk, risk_factors
+
+def generate_plot(dropout_risk):
+    """Creates a bar plot for dropout risk."""
+    fig, ax = plt.subplots()
+    colors = ['green', 'lightgreen', 'yellow', 'orange', 'red']
+    labels = ['Very Low Risk', 'Low Risk', 'Moderate Risk', 'High Risk', 'Very High Risk']
+    index = min(int(dropout_risk // 2), 4)
+
+    ax.bar([labels[index]], [dropout_risk], color=colors[index])
+    ax.set_ylim(0, 10)
+    ax.set_ylabel('Dropout Risk Score')
+    ax.set_title('Dropout Risk Prediction')
+
+    plt.savefig("dropout_plot.png")  # Save before using in PDF
+    return fig
+
+def remove_emojis(text):
+    """Removes all emojis and unsupported Unicode characters from text."""
+    emoji_pattern = re.compile("[\U00010000-\U0010ffff]", flags=re.UNICODE)
+    return emoji_pattern.sub("", text)
+
+def process_and_generate_report(**input_values):
+
+    """Processes input values and generates risk prediction along with a report."""
+    
+    dropout_risk,risk_factor = predict_dropout(**input_values)
+    insights = generate_dropout_insights(input_values,risk_factor)
+    cleaned_insights = remove_emojis(insights)
+    fig = generate_plot(dropout_risk)
+    pdf_filename = generate_pdf(input_values, dropout_risk, cleaned_insights)
+    
+
     return fig, insights, pdf_filename