Create app.py

app.py

@@ -0,0 +1,298 @@
+!pip install gradio pandas scikit-learn joblib
+
+
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+import gradio as gr
+import joblib
+
+# Load your dataset (assuming 'AIDA-PHQ-Updated.csv' is in the same directory as your script)
+df = pd.read_csv("AIDA-PHQ-Updated.csv")
+
+df.head()
+
+# Ordinal mappings (if not already applied)
+ordinal_mappings = {
+    'Not Applicable' : 0,
+    'Strongly disagree': 1,
+    'Disagree': 2,
+    'Neutral': 3,
+    'Agree': 4,
+    'Strongly agree': 5
+}
+
+ordinal_columns = [
+    'PoorAcademicPerformanceSelfPerception', 'AcademicCriticismSelfPerception',
+    'UnsatisfiedAcademicWorkloadSelfPerception', 'NonInterestSubjectOpinion',
+    'UnhappySubjectOpinion', 'NonInterestInstitutionOpinion',
+    'UnhappyInstitutionOpinion', 'ParentalStrictness', 'ParentalAcademicPressure',
+    'ParentalMarriagePressure', 'ParentalCareerPressure',
+    'ParentalStudyAbroadPressure', 'ParentalUnderstanding', 'SiblingBonding',
+    'ParentalRelationshipStability', 'PeerRelationship', 'TeacherSupport',
+    'PartnerRelationshipImpact', 'PhysicalViolenceExperience',
+    'SexualViolenceExperience', 'VerbalViolenceExperience',
+    'EmotionalViolenceExperience'
+]
+
+for col in ordinal_columns:
+    df[col] = df[col].map(ordinal_mappings)
+
+# Encode the Gender column
+from sklearn.preprocessing import LabelEncoder
+encoder = LabelEncoder()
+df['Gender'] = encoder.fit_transform(df['Gender'])
+
+df.head()
+
+# Split into X and y
+X = df.drop('DepressionLevel', axis=1)
+y = df['DepressionLevel']
+
+X.columns
+
+X.head()
+
+# Split into train and test sets
+random_state = 2024
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=random_state)
+
+# Standardize features
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+
+
+# Train Logistic Regression model
+logreg = LogisticRegression(C=10.0, solver='newton-cg')
+logreg.fit(X_train_scaled, y_train)
+
+
+# Save the model as a .bin file
+with open('model.bin', 'wb') as file:
+    joblib.dump(logreg, file)
+
+# Save the scaler as a .bin file
+with open('scaler.bin', 'wb') as file:
+    joblib.dump(scaler, file)
+
+def predict_depression_level_logreg(age, gender, cgpa, poor_academic_performance,
+                                    academic_criticism, unsatisfied_workload,
+                                    non_interest_subject, unhappy_subject,
+                                    non_interest_institution, unhappy_institution,
+                                    parental_strictness, parental_academic_pressure,
+                                    parental_marriage_pressure, parental_career_pressure,
+                                    parental_study_abroad, parental_understanding,
+                                    sibling_bonding, parental_relationship_stability,
+                                    peer_relationship, teacher_support,
+                                    partner_relationship_impact, physical_violence,
+                                    sexual_violence, verbal_violence, emotional_violence,
+                                    little_interest, feeling_down, sleeping_issue,
+                                    feeling_tired, poor_appetite, feeling_bad,
+                                    trouble_concentrating, slowness, self_harm):
+
+    # Convert gender to numeric
+    gender = 1 if gender == 'Female' else 0
+
+    # Define feature names matching those used during fitting
+    feature_names = [
+        'Age', 'Gender', 'CGPA', 'PoorAcademicPerformanceSelfPerception', 'AcademicCriticismSelfPerception',
+        'UnsatisfiedAcademicWorkloadSelfPerception', 'NonInterestSubjectOpinion', 'UnhappySubjectOpinion',
+        'NonInterestInstitutionOpinion', 'UnhappyInstitutionOpinion', 'ParentalStrictness', 'ParentalAcademicPressure',
+        'ParentalMarriagePressure', 'ParentalCareerPressure', 'ParentalStudyAbroadPressure', 'ParentalUnderstanding',
+        'SiblingBonding', 'ParentalRelationshipStability', 'PeerRelationship', 'TeacherSupport',
+        'PartnerRelationshipImpact', 'PhysicalViolenceExperience', 'SexualViolenceExperience', 'VerbalViolenceExperience',
+        'EmotionalViolenceExperience', 'little interest', 'feeling down', 'Sleeping issue', 'feeling tired',
+        'poor appetite', 'feeling bad', 'trouble concertrating', 'slowness', 'self harm'
+    ]
+
+    # Map ordinal columns to numerical values using ordinal_mappings
+    input_data = pd.DataFrame([[age, gender, cgpa, ordinal_mappings[poor_academic_performance],
+                                ordinal_mappings[academic_criticism], ordinal_mappings[unsatisfied_workload],
+                                ordinal_mappings[non_interest_subject], ordinal_mappings[unhappy_subject],
+                                ordinal_mappings[non_interest_institution], ordinal_mappings[unhappy_institution],
+                                ordinal_mappings[parental_strictness], ordinal_mappings[parental_academic_pressure],
+                                ordinal_mappings[parental_marriage_pressure], ordinal_mappings[parental_career_pressure],
+                                ordinal_mappings[parental_study_abroad], ordinal_mappings[parental_understanding],
+                                ordinal_mappings[sibling_bonding], ordinal_mappings[parental_relationship_stability],
+                                ordinal_mappings[peer_relationship], ordinal_mappings[teacher_support],
+                                ordinal_mappings[partner_relationship_impact], ordinal_mappings[physical_violence],
+                                ordinal_mappings[sexual_violence], ordinal_mappings[verbal_violence], ordinal_mappings[emotional_violence],
+                                little_interest, feeling_down, sleeping_issue, feeling_tired,
+                                poor_appetite, feeling_bad, trouble_concentrating, slowness, self_harm]],
+                              columns=feature_names)
+
+    input_data_scaled = scaler.transform(input_data)
+    prediction = logreg.predict(input_data_scaled)[0]
+    return str(prediction)
+
+
+# Define Gradio interface with proper input labels and output type
+inputs = [
+    gr.Slider(minimum=int(df['Age'].min()), maximum=int(df['Age'].max()), label="Age"),
+    gr.Dropdown(choices=["Male", "Female"], label="Gender"),
+    gr.Slider(minimum=float(df['CGPA'].min()), maximum=float(df['CGPA'].max()), label="CGPA")
+]
+
+
+# Updated labels for ordinal columns
+ordinal_labels = {
+    'PoorAcademicPerformanceSelfPerception': 'Your Academic Performance is poor.',
+    'AcademicCriticismSelfPerception': 'You experience Academic Criticism.',
+    'UnsatisfiedAcademicWorkloadSelfPerception': 'You are unsatisfied with your academic workload.',
+    'NonInterestSubjectOpinion': 'The subject you are studying is of non-interest to you.',
+    'UnhappySubjectOpinion': 'You are unhappy with the subject you are studying.',
+    'NonInterestInstitutionOpinion': 'You study at an institution of your non-interest.',
+    'UnhappyInstitutionOpinion': 'You are Unhappy with your institution.',
+
+    'ParentalStrictness': 'Your parents are strict.',
+    'ParentalAcademicPressure': 'You experience academic pressure from your parents.',
+    'ParentalMarriagePressure': 'You experience pressure to get married from your parents.',
+    'ParentalCareerPressure': 'You experience career pressure from your parents.',
+    'ParentalStudyAbroadPressure': 'You experience pressure to study abroad from your parents.',
+    'ParentalUnderstanding': 'Your have poor understanding with your parents.',
+    'SiblingBonding': 'You have poor bonding with your siblings.',
+    'ParentalRelationshipStability': 'Your parents have unstable relationship.',
+
+    'PeerRelationship': 'You have poor relationship with your peers.',
+    'TeacherSupport': 'Teachers do not support you.',
+    'PartnerRelationshipImpact': 'You have poor relationship with your partner.',
+    'PhysicalViolenceExperience': 'You have experience physical violence.',
+    'SexualViolenceExperience': 'You have experience sexual violence.',
+    'VerbalViolenceExperience': 'You have experience verbal violence.',
+    'EmotionalViolenceExperience': 'You have experienced emotional violence.',
+}
+
+# Add radio buttons for ordinal columns with updated labels
+for col in ordinal_columns:
+    inputs.append(gr.Radio(choices=list(ordinal_mappings.keys()), label=ordinal_labels[col]))
+
+
+# Add sliders for the remaining inputs
+additional_inputs = [
+    gr.Slider(minimum=0, maximum=5, step=1, label="How has your interest changed over work and activities? (0= No change)"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="How often do you feel down?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="Do you struggle to sleep?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="How often do you feel tired?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="How has your appetite changed?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="How often do you feel bad about yourself?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="How has your concentration levels changed?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="Do you feel slow?"),
+    gr.Slider(minimum=0, maximum=5, step=1, label="Have you had suicidal thoughts?")
+]
+
+inputs.extend(additional_inputs)
+
+# # Sample input values (these should match the features and their order in your function)
+# sample_input = {
+#     "Age": 25,
+#     "Gender": "Female",  # Assuming string value for Gender
+#     "CGPA": 3.5,
+#     "PoorAcademicPerformanceSelfPerception": "Disagree",  # String value, needs mapping
+#     "AcademicCriticismSelfPerception": "Neutral",  # String value, needs mapping
+#     "UnsatisfiedAcademicWorkloadSelfPerception": "Strongly disagree",  # String value, needs mapping
+#     "NonInterestSubjectOpinion": "Disagree",  # String value, needs mapping
+#     "UnhappySubjectOpinion": "Neutral",  # String value, needs mapping
+#     "NonInterestInstitutionOpinion": "Strongly disagree",  # String value, needs mapping
+#     "UnhappyInstitutionOpinion": "Disagree",  # String value, needs mapping
+#     "ParentalStrictness": "Strongly agree",  # String value, needs mapping
+#     "ParentalAcademicPressure": "Agree",  # String value, needs mapping
+#     "ParentalMarriagePressure": "Neutral",  # String value, needs mapping
+#     "ParentalCareerPressure": "Strongly disagree",  # String value, needs mapping
+#     "ParentalStudyAbroadPressure": "Neutral",  # String value, needs mapping
+#     "ParentalUnderstanding": "Strongly agree",  # String value, needs mapping
+#     "SiblingBonding": "Strongly agree",  # String value, needs mapping
+#     "ParentalRelationshipStability": "Neutral",  # String value, needs mapping
+#     "PeerRelationship": "Agree",  # String value, needs mapping
+#     "TeacherSupport": "Strongly agree",  # String value, needs mapping
+#     "PartnerRelationshipImpact": "Neutral",  # String value, needs mapping
+#     "PhysicalViolenceExperience": 0,
+#     "SexualViolenceExperience": 1,
+#     "VerbalViolenceExperience": 0,
+#     "EmotionalViolenceExperience": 2,
+#     "little interest": 1,
+#     "feeling down": 3,
+#     "Sleeping issue": 2,
+#     "feeling tired": 4,
+#     "poor appetite": 2,
+#     "feeling bad": 3,
+#     "trouble concertrating": 1,
+#     "slowness": 2,
+#     "self harm": 0
+# }
+
+# # Convert the sample input dictionary to a DataFrame
+# sample_df = pd.DataFrame([sample_input])
+
+# # Map ordinal columns to numerical values using ordinal_mappings
+# for col in ordinal_columns:
+#     sample_df[col] = sample_df[col].map(ordinal_mappings)
+
+# # Convert gender to numeric
+# sample_df['Gender'] = 1 if sample_df['Gender'].iloc[0] == 'Female' else 0
+
+# # Scale the input data using the scaler from your model
+# sample_df_scaled = scaler.transform(sample_df)
+
+# # Predict using your function
+# prediction = predict_depression_level_logreg(*sample_df_scaled[0])
+
+# # Print or use the prediction as needed
+# print("Predicted Depression Level:", prediction)
+
+
+output = gr.Textbox(label="Predicted Depression Level")
+
+# Create Gradio interface
+iface = gr.Interface(fn=predict_depression_level_logreg, inputs=inputs, outputs=output, title="Understand your Depression Levels",
+                     description="A questionnaire to determine potential depression severity using the questions below - ")
+
+iface.launch(debug=True, share=True)
+
+# #importing libraries
+# import numpy as np
+# import lime
+# # import lime.lime_tabular
+# from lime import lime_tabular
+
+# # Training Logistic Regression classifier
+# model = LogisticRegression()
+# model.fit(X_train, y_train)
+
+# # Defining the lime explainer
+# explainer = lime_tabular.LimeTabularExplainer(
+#     training_data=np.array(X_train),
+#     feature_names=X_train.columns,
+#     class_names=['MINIMAL','MILD','Moderate','ModeratelySevere','Severe'],
+#     mode='classification'
+# )
+
+# #importing libraries
+# import numpy as np
+# import lime
+# # import lime.lime_tabular
+# from lime import lime_tabular
+
+# # Training Logistic Regression classifier
+# model = LogisticRegression()
+# model.fit(X_train, y_train)
+
+# # Defining the lime explainer
+# explainer = lime_tabular.LimeTabularExplainer(
+#     training_data=np.array(X_train),
+#     feature_names=X_train.columns,
+#     class_names=['MINIMAL','MILD','Moderate','ModeratelySevere','Severe'],
+#     mode='classification'
+# )
+
+# exp = explainer.explain_instance(
+#     data_row=X_test.iloc[5],
+#     predict_fn=model.predict_proba, num_features = 12
+# )
+
+# exp.show_in_notebook(show_table=True)
+