logistic model on cleaned data till 23oct

- 61.71 percent accuracy

scripts/logistic2.py

@@ -0,0 +1,86 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+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 = ['deviceId', 'led1Buffer', 'led1Sample', 'led2Buffer', 'led2Sample']
+for col in categorical_cols:
+    data[col] = label_encoder.fit_transform(data[col])
+
+X = data[['deviceId', 'led1Buffer', 'led1Sample', 'led2Buffer', 'led2Sample']]
+y = data['classificationResult']
+
+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)
+
+model = LogisticRegression()
+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)
+#sns.heatmap(pd.DataFrame(classification_report_result).iloc[:-1, :].T, annot=True)
+
+
+# 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: 0.6171938361719383
+# Classification Report:
+#                                                                           precision    recall  f1-score   support
+
+#                Inconclusive. Repeat with test with lower volume of blood       0.00      0.00      0.00         6
+# Inconclusive. Very low Absorbance - Repeat test with Higher Blood Volume       0.17      0.05      0.07        21
+#                                         Negative Borderline. Repeat Test       0.00      0.00      0.00       167
+#                                                                   Normal       0.69      0.89      0.78       749
+#                          Positive for Sickle Cell. HPLC for Confirmation       0.00      0.00      0.00        41
+#                                                      Sickle Cell Disease       0.28      0.24      0.26        38
+#                                                        Sickle Cell Trait       0.37      0.39      0.38       211
+
+#                                                                 accuracy                           0.62      1233
+#                                                                macro avg       0.22      0.22      0.21      1233
+#                                                             weighted avg       0.49      0.62      0.55      1233
+
+
+# with open('logistic_regression_model.pkl', 'wb') as model_file:
+#     pickle.dump(model, model_file)
+
+
+# with open('logistic_regression_model.pkl', 'rb') as model_file:
+#     loaded_model = pickle.load(model_file)
+
+# new_data = pd.DataFrame({'Age': [30], 'Gender': ['MALE'], 'Caste': ['SC'], 'Category': [''], 'Marital Status': ['Single']})
+# predicted_result = loaded_model.predict(new_data)
+# print(predicted_result)