import pandas as pd import numpy as np from sklearn.preprocessing import StandardScaler…
- User
import pandas as pd import numpy as np from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split, KFold from sklearn.metrics import accuracy_score from sklearn.neighbors import NearestNeighbors
class BMFK: def init(self, n_neighbors=5, m=2, p=2, q=2): self.n_neighbors = n_neighbors self.m = m # fuzzy strength parameter self.p = p # Bonferroni p parameter self.q = q # Bonferroni q parameter
def fit(self, X, y): self.X = X self.y = y self.classes = np.unique(y) self.nn = NearestNeighbors(n_neighbors=self.n_neighbors, metric='minkowski', p=2) self.nn.fit(X) def bonferroni_mean(self, values): n = len(values) if n <= 1: return np.mean(values) # Return simple mean if there's only one value sum_pq = 0 for i in range(n): for j in range(n): if i != j: sum_pq += values[i]**self.p * values[j]**self.q return (sum_pq / (n * (n-1)))**(1 / (self.p + self.q)) def predict(self, X): predictions = [] for x in X: distances, indices = self.nn.kneighbors([x]) neighbors = self.X[indices[0]] neighbor_labels = self.y[indices[0]] # Calculate fuzzy memberships memberships = 1 / (distances[0] ** (2 / (self.m - 1)) + 1e-8) memberships /= np.sum(memberships) # Calculate class memberships using Bonferroni mean class_memberships = {} for c in self.classes: class_indices = neighbor_labels == c if np.any(class_indices): class_memberships[c] = self.bonferroni_mean(memberships[class_indices]) else: class_memberships[c] = 0 # Predict the class with highest membership predictions.append(max(class_memberships, key=class_memberships.get)) return np.array(predictions)Load the dataset
file_path = "PCOS_data_without_infertility.xlsx" df = pd.read_excel(file_path, sheet_name="Full_new")
Data Preprocessing
df = df.drop(columns=['Sl. No', 'Patient File No.', 'Unnamed: 44']) df = df.apply(pd.to_numeric, errors='coerce') df.fillna(df.median(), inplace=True)
Encode categorical columns
categorical_columns = ['Blood Group', 'Cycle(R/I)', 'Pregnant(Y/N)', 'Weight gain(Y/N)', 'hair growth(Y/N)', 'Skin darkening (Y/N)', 'Hair loss(Y/N)', 'Pimples(Y/N)', 'Fast food (Y/N)', 'Reg.Exercise(Y/N)'] for col in categorical_columns: if col in df.columns: df[col] = df[col].astype('category').cat.codes
Split into features and target
X = df.drop(columns=['PCOS (Y/N)']) y = df['PCOS (Y/N)'].values # Convert to numpy array
Standardize features
scaler = StandardScaler() X_scaled = scaler.fit_transform(X)
Define the different feature sets
ensemble_selected_features = ['Follicle No. (L)', 'hair growth(Y/N)', 'Follicle No. (R)', 'Cycle(R/I)', 'Fast food (Y/N)', 'AMH(ng/mL)', 'Skin darkening (Y/N)', 'Weight gain(Y/N)', 'Pimples(Y/N)', 'Cycle length(days)', 'Hip(inch)', 'Weight (Kg)', 'FSH/LH', 'FSH(mIU/mL)']
rl_selected_features = [' Age (yrs)', 'Weight (Kg)', 'Pulse rate(bpm) ', 'RR (breaths/min)', 'Hb(g/dl)', 'Cycle(R/I)', 'Cycle length(days)', 'Marraige Status (Yrs)', ' I beta-HCG(mIU/mL)', 'FSH(mIU/mL)', 'Waist(inch)', 'Waist:Hip Ratio', 'TSH (mIU/L)', 'AMH(ng/mL)', 'Vit D3 (ng/mL)', 'PRG(ng/mL)', 'RBS(mg/dl)', 'Weight gain(Y/N)', 'hair growth(Y/N)', 'Skin darkening (Y/N)', 'Pimples(Y/N)', 'BP _Systolic (mmHg)', 'BP _Diastolic (mmHg)', 'Follicle No. (L)', 'Follicle No. (R)']
proposed_selected_features = ['Follicle No. (L)', 'hair growth(Y/N)', 'Follicle No. (R)', 'Cycle(R/I)', 'Fast food (Y/N)', 'Skin darkening (Y/N)', 'Cycle length(days)', 'FSH/LH']
1. BMFK on Ensemble Selected Features
X_ensemble = X_scaled[:, [X.columns.get_loc(feature) for feature in ensemble_selected_features]]
2. BMFK on RL Selected Features
X_rl = X_scaled[:, [X.columns.get_loc(feature) for feature in rl_selected_features]]
3. BMFK on Proposed BMFK Selected Features
X_proposed = X_scaled[:, [X.columns.get_loc(feature) for feature in proposed_selected_features]]
4. BMFK on All Features (no feature selection)
X_all = X_scaled # Use all features
Helper function to run cross-validation
def run_bmfk_cv(X, y): kf = KFold(n_splits=10, shuffle=True, random_state=42) accuracies = [] for train_idx, test_idx in kf.split(X): X_train, X_test = X[train_idx], X[test_idx] y_train, y_test = y[train_idx], y[test_idx]
model = BMFK(n_neighbors=5, m=2, p=1, q=1) model.fit(X_train, y_train) y_pred = model.predict(X_test) accuracy = accuracy_score(y_test, y_pred) accuracies.append(accuracy) return np.mean(accuracies)Run BMFK for all four cases
accuracy_ensemble = run_bmfk_cv(X_ensemble, y) accuracy_rl = run_bmfk_cv(X_rl, y) accuracy_proposed = run_bmfk_cv(X_proposed, y) accuracy_all = run_bmfk_cv(X_all, y)
print(f"BMFK on Ensemble Selected Features Accuracy: {accuracy_ensemble:.4f}") print(f"BMFK on RL Selected Features Accuracy: {accuracy_rl:.4f}") print(f"BMFK on Proposed Selected Features Accuracy: {accuracy_proposed:.4f}") print(f"BMFK on All Features Accuracy: {accuracy_all:.4f}")
use svm here instead of bmfk
- Assistant
import pandas as pd import numpy as np from sklearn.preprocessing import StandardScaler from sklearn.model_selection import KFold from sklearn.metrics import accuracy_score from sklearn.svm import SVC # Load the dataset file_path = "PCOS_data_without_infertility.xlsx" df = pd.read_excel(file_path, sheet_name="Full_new") # Data Preprocessing df = df.drop(columns=['Sl. No', 'Patient File No.', 'Unnamed: 44']) df = df.apply(pd.to_numeric, errors='coerce') df.fillna(df.median(), inplace=True) # Encode categorical columns categorical_columns = ['Blood Group', 'Cycle(R/I)', 'Pregnant(Y/N)', 'Weight gain(Y/N)', 'hair growth(Y/N)', 'Skin darkening (Y/N)', 'Hair loss(Y/N)', 'Pimples(Y/N)', 'Fast food (Y/N)', 'Reg.Exercise(Y/N)'] for col in categorical_columns: if col in df.columns: df[col] = df[col].astype('category').cat.codes # Split into features and target X = df.drop(columns=['PCOS (Y/N)']) y = df['PCOS (Y/N)'].values # Convert to numpy array # Standardize features scaler = StandardScaler() X_scaled = scaler.fit_transform(X) # Define the different feature sets ensemble_selected_features = ['Follicle No. (L)', 'hair growth(Y/N)', 'Follicle No. (R)', 'Cycle(R/I)', 'Fast food (Y/N)', 'AMH(ng/mL)', 'Skin darkening (Y/N)', 'Weight gain(Y/N)', 'Pimples(Y/N)', 'Cycle length(days)', 'Hip(inch)', 'Weight (Kg)', 'FSH/LH', 'FSH(mIU/mL)'] rl_selected_features = [' Age (yrs)', 'Weight (Kg)', 'Pulse rate(bpm) ', 'RR (breaths/min)', 'Hb(g/dl)', 'Cycle(R/I)', 'Cycle length(days)', 'Marraige Status (Yrs)', ' I beta-HCG(mIU/mL)', 'FSH(mIU/mL)', 'Waist(inch)', 'Waist:Hip Ratio', 'TSH (mIU/L)', 'AMH(ng/mL)', 'Vit D3 (ng/mL)', 'PRG(ng/mL)', 'RBS(mg/dl)', 'Weight gain(Y/N)', 'hair growth(Y/N)', 'Skin darkening (Y/N)', 'Pimples(Y/N)', 'BP _Systolic (mmHg)', 'BP _Diastolic (mmHg)', 'Follicle No. (L)', 'Follicle No. (R)'] proposed_selected_features = ['Follicle No. (L)', 'hair growth(Y/N)', 'Follicle No. (R)', 'Cycle(R/I)', 'Fast food (Y/N)', 'Skin darkening (Y/N)', 'Cycle length(days)', 'FSH/LH'] # 1. SVM on Ensemble Selected Features X_ensemble = X_scaled[:, [X.columns.get_loc(feature) for feature in ensemble_selected_features]] # 2. SVM on RL Selected Features X_rl = X_scaled[:, [X.columns.get_loc(feature) for feature in rl_selected_features]] # 3. SVM on Proposed Selected Features X_proposed = X_scaled[:, [X.columns.get_loc(feature) for feature in proposed_selected_features]] # 4. SVM on All Features (no feature selection) X_all = X_scaled # Use all features # Helper function to run cross-validation def run_svm_cv(X, y, svm_params=None): if svm_params is None: svm_params = {} kf = KFold(n_splits=10, shuffle=True, random_state=42) accuracies = [] for train_idx, test_idx in kf.split(X): X_train, X_test = X[train_idx], X[test_idx] y_train, y_test = y[train_idx], y[test_idx] model = SVC(**svm_params) model.fit(X_train, y_train) y_pred = model.predict(X_test) accuracy = accuracy_score(y_test, y_pred) accuracies.append(accuracy) return np.mean(accuracies) # Run SVM for all four cases svm_params = {'kernel': 'rbf', 'C': 1, 'gamma': 'scale'} # You can adjust these parameters accuracy_ensemble = run_svm_cv(X_ensemble, y, svm_params) accuracy_rl = run_svm_cv(X_rl, y, svm_params) accuracy_proposed = run_svm_cv(X_proposed, y, svm_params) accuracy_all = run_svm_cv(X_all, y, svm_params) print(f"SVM on Ensemble Selected Features Accuracy: {accuracy_ensemble:.4f}") print(f"SVM on RL Selected Features Accuracy: {accuracy_rl:.4f}") print(f"SVM on Proposed Selected Features Accuracy: {accuracy_proposed:.4f}") print(f"SVM on All Features Accuracy: {accuracy_all:.4f}")This code replaces the BMFK classifier with an SVM classifier and retains the same preprocessing and feature selection steps. It applies 10-fold cross-validation for each of the four feature sets using the SVM classifier and reports the mean accuracy for each. Adjust the
svm_paramsdictionary to tune the SVM's hyperparameters as needed.