Upload 5 files

Dockerfile

@@ -0,0 +1,17 @@
+# Use Python 3.10 as the base image
+FROM python:3.10
+
+# Set the working directory
+WORKDIR /app
+
+# Copy all files to the container
+COPY . /app
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Expose port 7860
+EXPOSE 7860
+
+# Run the Flask app
+CMD ["python", "server.py"]

index.py

@@ -0,0 +1,166 @@
+import pandas as pd
+import numpy as np
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import recall_score,accuracy_score,roc_auc_score,average_precision_score,roc_curve,auc
+from sklearn.feature_selection import RFECV
+import seaborn as sns
+from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
+from sklearn.model_selection import  cross_val_score,train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.impute import KNNImputer
+import joblib
+df=pd.read_excel('appendicitis.xlsx')
+columns=['AppendixDiameter','ReboundTenderness','CoughingPain','FreeFluids','MigratoryPain','BodyTemp','KetonesInUrine','Nausea',
+         'WBCCount','NeutrophilPerc','CRPEntry','Peritonitis','DiagnosisByCriteria']
+
+df=df[columns]
+
+usg_col =['AppendixDiameter','FreeFluids']
+
+df[usg_col]=df[usg_col].fillna(0)
+
+mapping ={
+    '+++' : 3,
+    '++': 2,
+    '+': 1,
+    'no':0,
+    'yes':1,
+    'local':1,
+    'generalised':2,
+    'normal':0,
+    'noAppendicitis':0,
+    'appendicitis':1
+}
+
+for col in df.columns:
+    df[col]=df[col].replace(mapping)
+
+x = df.iloc[:, 0:-1]  
+y = df.iloc[:, -1]
+
+
+x_tempi, x_testi, y_temp, y_testi = train_test_split(x,y,test_size=0.2,random_state=17)
+x_traini,x_vali,y_traini,y_vali = train_test_split(x_tempi,y_temp,test_size=0.25,random_state=17)
+
+imputer_train = KNNImputer(n_neighbors=5)
+imputer_val = KNNImputer(n_neighbors=5)
+imputer_test = KNNImputer(n_neighbors=5)
+imputer_temp=KNNImputer(n_neighbors=5)
+
+x_temp=pd.DataFrame(imputer_temp.fit_transform(x_tempi),columns=x_tempi.columns,index=x_tempi.index)
+x_train = pd.DataFrame(imputer_train.fit_transform(x_traini), columns=x_traini.columns, index=x_traini.index)
+x_val = pd.DataFrame(imputer_val.fit_transform(x_vali), columns=x_vali.columns, index=x_vali.index)
+x_test = pd.DataFrame(imputer_test.fit_transform(x_testi), columns=x_testi.columns, index=x_testi.index)
+
+y_train=y_traini.squeeze()
+y_val=y_vali.squeeze()
+y_test=y_testi.squeeze()
+y_temp=y_temp.squeeze()
+
+columns_round = [ 'MigratoryPain','ReboundTenderness','CoughingPain','Peritonitis','KetonesInUrine','Nausea']
+
+for col in columns_round:
+    if col in x_temp.columns:
+        x_temp[col]=x_temp[col].round().astype(int)
+    if col in x_train.columns:
+        x_train[col] = x_train[col].round().astype(int)
+    if col in x_val.columns:
+        x_val[col] = x_val[col].round().astype(int)
+    if col in x_test.columns:
+        x_test[col] = x_test[col].round().astype(int) 
+
+
+rf_model=RandomForestClassifier(
+    n_estimators=700,
+    min_samples_split=12,
+    min_samples_leaf=1,
+    max_depth=35,
+    random_state=17
+)
+scores = cross_val_score(rf_model, x_train, y_train, cv=10, scoring='accuracy', n_jobs=2)
+print("Mean cross_val accuracy Score:", scores.mean())
+print("Standard Deviation of cross_val accuracy Scores:", scores.std())
+
+rf_model.fit(x_train,y_train)
+joblib.dump(rf_model, 'rf_model.pkl')
+
+
+
+# y_pred_prob=rf_model.predict_proba(x_val)[:,1]
+# fpr, tpr, thresholds = roc_curve(y_val, y_pred_prob)
+# youden_index = tpr - fpr
+# optimal_idx = np.argmax(youden_index)
+# optimal_threshold = thresholds[optimal_idx]
+
+# distances = np.sqrt((1 - tpr)**2 + fpr**2)
+# optimal_idx = np.argmin(distances)
+# optimal_threshold = thresholds[optimal_idx]
+
+# print(f"Optimal Threshold: {optimal_threshold}")
+
+threshold=0.7032966204148201
+
+y_pred_prob=rf_model.predict_proba(x_val)[:,1]
+y_thres=(y_pred_prob >= threshold).astype(int)
+auc_score = roc_auc_score(y_val, y_pred_prob)
+print("Val AUC:", auc_score)
+val_conf_matrix = confusion_matrix(y_val, y_thres)
+TNv, FPv, FNv, TPv = val_conf_matrix.ravel()
+val_sensitivity = TPv / (TPv + FNv)
+val_specificity = TNv / (TNv + FPv)
+val_ppv = TPv/(TPv+FPv)
+val_npv = TNv/(TNv+FNv)
+print(f"Sensitivity: {val_sensitivity:.3f} ({val_sensitivity * 100:.2f}%)")
+print(f"Specificity: {val_specificity:.3f} ({val_specificity * 100:.2f}%)")
+
+print (f"Positive predictive value : {val_ppv:.3f}({val_ppv*100:.2f}%)")
+print (f"Negative predictive value : {val_npv:.3f}({val_npv*100:.2f}%)")
+
+print("Val Confusion Matrix:\n", val_conf_matrix)
+val_acu=accuracy_score(y_val,y_thres)
+print("Val accuracy score:",val_acu)
+
+y_test_prob=rf_model.predict_proba(x_test)[:,1]
+y_thres_test=(y_test_prob >= threshold).astype(int)
+auc_score = roc_auc_score(y_test, y_test_prob)
+print("Test AUC:", auc_score)
+test_conf_matrix = confusion_matrix(y_test, y_thres_test)
+print("Test Confusion Matrix:\n", test_conf_matrix)
+TNt, FPt, FNt, TPt = test_conf_matrix.ravel()
+test_sensitivity = TPt / (TPt + FNt)
+test_specificity = TNt / (TNt + FPt)
+
+test_ppv = TPt/(TPt+FPt)
+test_npv = TNt/(TNt+FNt)
+
+print(f"Sensitivity: {test_sensitivity:.3f} ({test_sensitivity * 100:.2f}%)")
+print(f"Specificity: {test_specificity:.3f} ({test_specificity * 100:.2f}%)")
+
+print (f"Positive predictive value : {test_ppv:.3f}({test_ppv*100:.2f}%)")
+print (f"Negative predictive value : {test_npv:.3f}({test_npv*100:.2f}%)")
+
+test_acu=accuracy_score(y_test,y_thres_test)
+print("Test Accuracy score:",test_acu)
+rf_model.fit(x_temp,y_temp)
+y_test1_prob=rf_model.predict_proba(x_test)[:,1]
+y_thres1_test=(y_test1_prob >= threshold).astype(int)
+auc_score1 = roc_auc_score(y_test, y_test1_prob)
+print("Test AUC:", auc_score1)
+test1_conf_matrix = confusion_matrix(y_test, y_thres1_test)
+print("Test Confusion Matrix:\n", test1_conf_matrix)
+TNt1, FPt1, FNt1, TPt1 = test1_conf_matrix.ravel()
+
+test_sensitivity1 = TPt1 / (TPt1 + FNt1)
+test_specificity1 = TNt1 / (TNt1 + FPt1)
+
+test_ppv1 = TPt1/(TPt1+FPt1)
+test_npv1 = TNt1/(TNt1+FNt1)
+
+print(f"Sensitivity: {test_sensitivity1:.3f} ({test_sensitivity1 * 100:.2f}%)")
+print(f"Specificity: {test_specificity1:.3f} ({test_specificity1 * 100:.2f}%)")
+
+print (f"Positive predictive value : {test_ppv1:.3f}({test_ppv1*100:.2f}%)")
+print (f"Negative predictive value : {test_npv1:.3f}({test_npv1*100:.2f}%)")
+
+test1_acu=accuracy_score(y_test,y_thres1_test)
+print("Test Accuracy score:",test1_acu)

requirements.txt

@@ -0,0 +1,101 @@
+absl-py==2.1.0
+alembic==1.13.3
+asttokens==2.4.1
+astunparse==1.6.3
+blinker==1.8.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+Choco==1.0.5
+click==8.1.7
+cloudpickle==3.1.0
+colorama==0.4.6
+colorlog==6.8.2
+comm==0.2.2
+contourpy==1.3.0
+cycler==0.12.1
+debugpy==1.8.6
+decorator==5.1.1
+et_xmlfile==2.0.0
+executing==2.1.0
+Flask==3.0.3
+Flask-Cors==5.0.0
+flatbuffers==24.3.25
+fonttools==4.54.1
+gast==0.6.0
+google-pasta==0.2.0
+gower==0.1.2
+greenlet==3.1.1
+grpcio==1.66.2
+h5py==3.12.1
+idna==3.10
+ipykernel==6.29.5
+ipython==8.28.0
+itsdangerous==2.2.0
+jedi==0.19.1
+Jinja2==3.1.4
+joblib==1.4.2
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+keras==3.6.0
+kiwisolver==1.4.7
+libclang==18.1.1
+llvmlite==0.43.0
+Mako==1.3.5
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+ml-dtypes==0.4.1
+namex==0.0.8
+nest-asyncio==1.6.0
+numba==0.60.0
+numpy==1.26.4
+openpyxl==3.1.5
+opt_einsum==3.4.0
+optree==0.13.0
+optuna==4.0.0
+packaging==24.1
+pandas==2.2.3
+parso==0.8.4
+pillow==10.4.0
+platformdirs==4.3.6
+prompt_toolkit==3.0.48
+protobuf==4.25.5
+psutil==6.0.0
+pure_eval==0.2.3
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+requests==2.32.3
+rich==13.9.2
+scikit-learn==1.5.2
+scipy==1.14.1
+seaborn==0.13.2
+setuptools==75.1.0
+shap==0.46.0
+six==1.16.0
+slicer==0.0.8
+SQLAlchemy==2.0.36
+stack-data==0.6.3
+tensorboard==2.17.1
+tensorboard-data-server==0.7.2
+tensorflow==2.17.0
+tensorflow-intel==2.17.0
+termcolor==2.4.0
+threadpoolctl==3.5.0
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+wcwidth==0.2.13
+Werkzeug==3.0.4
+wheel==0.44.0
+wrapt==1.16.0
+xgboost==2.1.1

rf_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b44ae921d87879451237b3195675f3c475cbd1fd904c734c12f16bd0a0be1f
+size 1935849

server.py

@@ -0,0 +1,51 @@
+from flask import Flask, request, render_template
+import pandas as pd
+import joblib
+
+app = Flask(__name__)
+
+# Load your pre-trained model
+model = joblib.load('rf_model.pkl')
+threshold = 0.7032966204148201
+
+@app.route('/')
+def home():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    try:
+        # Extract values from the form
+        features = [
+            float(request.form.get('AppendixDiameter')),
+            float(request.form.get('ReboundTenderness')),
+            float(request.form.get('CoughingPain')),
+            float(request.form.get('FreeFluids')),
+            float(request.form.get('MigratoryPain')),
+            float(request.form.get('BodyTemp')),
+            float(request.form.get('KetonesInUrine')),
+            float(request.form.get('Nausea')),
+            float(request.form.get('WBCCount')),
+            float(request.form.get('NeutrophilPerc')),
+            float(request.form.get('CRPEntry')),
+            float(request.form.get('Peritonitis'))
+        ]
+        print("features",features)
+    except Exception as e:
+        return render_template('index.html', prediction_text="Error in input: " + str(e))
+    
+    # Create a DataFrame with proper column names
+    columns = ['AppendixDiameter', 'ReboundTenderness', 'CoughingPain', 'FreeFluids', 'MigratoryPain',
+               'BodyTemp', 'KetonesInUrine', 'Nausea', 'WBCCount', 'NeutrophilPerc', 'CRPEntry', 'Peritonitis']
+    data = pd.DataFrame([features], columns=columns)
+    
+    # Get the predicted probability and apply your threshold
+    pred_prob = model.predict_proba(data)[0][1]
+    prediction = 1 if pred_prob >= threshold else 0
+    
+    result = "Appendicitis" if prediction == 1 else "No Appendicitis"
+    
+    return render_template('index.html', prediction_text=f"Prediction: {result}")
+
+if __name__ == "__main__":
+    app.run(debug=True)