kneighbors with 75.02 percent accuracy

2023-10-25 02:33:42 +05:30
parent 1cf6324326
commit 64f198a384
1 changed files with 90 additions and 0 deletions
--- a/scripts/kneighbors.py
+++ b/scripts/kneighbors.py
@@ -0,0 +1,90 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import pickle
+import statsmodels.api as sm
+import matplotlib.pyplot as plt
+import seaborn as sns
+import os
+
+curdir = os.getcwd()
+path_delim = '/'
+data = pd.read_excel(curdir + path_delim + 'data/tests_24_10_2023_20_53_cleaned.xlsx', sheet_name="data")
+data = data.dropna()
+print(data)
+
+data.plot()
+
+label_encoder = LabelEncoder()
+categorical_cols = ['calculatedRatio', 'led1Buffer', 'led1Sample', 'led2Buffer', 'led2Sample']
+# for col in categorical_cols:
+#     data[col] = label_encoder.fit_transform(data[col])
+
+X = data[['calculatedRatio', 'led1Buffer', 'led1Sample', 'led2Buffer', 'led2Sample']]
+y = data['classificationResult']
+
+print(X)
+corr = X.corr()
+print(corr)
+sm.graphics.plot_corr(corr, xnames=list(corr.columns))
+plt.show()
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Change the classifier to KNeighborsClassifier
+model = KNeighborsClassifier(n_neighbors=5)  # You can adjust the number of neighbors as needed
+model.fit(X_train, y_train)
+
+y_pred = model.predict(X_test)
+
+accuracy = accuracy_score(y_test, y_pred)
+classification_report_result = classification_report(y_test, y_pred)
+
+# Calculate the confusion matrix
+confusion = confusion_matrix(y_test, y_pred)
+
+# Plot the confusion matrix using Seaborn
+plt.figure(figsize=(8, 6))
+sns.heatmap(confusion, annot=True, fmt='d', cmap='Blues', linewidths=0.5)
+plt.xlabel('Predicted')
+plt.ylabel('Actual')
+plt.title('Confusion Matrix')
+# plt.show()
+
+print(f"Accuracy: {accuracy}")
+print("Classification Report:")
+print(classification_report_result)
+
+# Accuracy: 0.7502027575020276
+# Classification Report:
+#                                                                           precision    recall  f1-score   support
+
+#                Inconclusive. Repeat with test with lower volume of blood       0.50      0.17      0.25         6
+# Inconclusive. Very low Absorbance - Repeat test with Higher Blood Volume       0.50      0.48      0.49        21
+#                                         Negative Borderline. Repeat Test       0.51      0.51      0.51       167
+#                                                                   Normal       0.85      0.92      0.88       749
+#                          Positive for Sickle Cell. HPLC for Confirmation       0.21      0.17      0.19        41
+#                                                      Sickle Cell Disease       0.67      0.32      0.43        38
+#                                                        Sickle Cell Trait       0.66      0.55      0.60       211
+
+#                                                                 accuracy                           0.75      1233
+#                                                                macro avg       0.56      0.45      0.48      1233
+#                                                             weighted avg       0.74      0.75      0.74      1233
+
+# Save the KNeighborsClassifier model
+with open('kneighbors_classifier_model.pkl', 'wb') as model_file:
+    pickle.dump(model, model_file)
+
+with open('kneighbors_classifier_model.pkl', 'rb') as model_file:
+    loaded_model = pickle.load(model_file)
+
+# Define new_data as needed for prediction
+# new_data = pd.DataFrame({'calculatedRatio': [0.17500836], 'led1Buffer': [24843.33], 'led1Sample': [19678], 'led2Buffer': [26715.33], 'led2Sample': [13842.67]})
+# new_data = pd.DataFrame({'calculatedRatio': [0.231057205], 'led1Buffer': [23776.33], 'led1Sample': [16286], 'led2Buffer': [26401.67], 'led2Sample': [6952.67]})
+new_data = pd.DataFrame({'calculatedRatio': [0.175881142], 'led1Buffer': [24256], 'led1Sample': [16303], 'led2Buffer': [27016.33], 'led2Sample': [4612.67]})
+# new_data = new_data.apply(lambda col: label_encoder.transform(col))
+print(new_data)
+predicted_result = loaded_model.predict(new_data)
+print(predicted_result)