hpos-data/scripts/logistic2.py

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, roc_curve, roc_auc_score
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']

# 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)

# # dataset: [6163 rows x 15 columns]
# # Accuracy: 0.6593673965936739
# # 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       0.88      0.71      0.79        21
# #                                         Negative Borderline. Repeat Test       0.11      0.01      0.01       167
# #                                                                   Normal       0.80      0.88      0.84       749
# #                          Positive for Sickle Cell. HPLC for Confirmation       0.00      0.00      0.00        41
# #                                                      Sickle Cell Disease       0.25      0.16      0.19        38
# #                                                        Sickle Cell Trait       0.37      0.62      0.46       211

# #                                                                 accuracy                           0.66      1233
# #                                                                macro avg       0.34      0.34      0.33      1233
# #                                                             weighted avg       0.58      0.66      0.61      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({'calculatedRatio': [0.126976079], 'led1Buffer': [24313.67], 'led1Sample': [20531], 'led2Buffer': [26565], 'led2Sample': [9975.33]}) #Normal
# new_data = pd.DataFrame({'calculatedRatio': [0.17500836], 'led1Buffer': [24843.33], 'led1Sample': [19678], 'led2Buffer': [26715.33], 'led2Sample': [13842.67]}) #SCT
# new_data = pd.DataFrame({'calculatedRatio': [0.251395102], 'led1Buffer': [24244], 'led1Sample': [17475], 'led2Buffer': [27059.67], 'led2Sample': [9258.33]}) #SCD
# new_data = pd.DataFrame({'calculatedRatio': [0.251061035], 'led1Buffer': [24172], 'led1Sample': [19345], 'led2Buffer': [26918], 'led2Sample': [12964.33]})
# new_data = pd.DataFrame({'calculatedRatio': [0.242851779], 'led1Buffer': [25087.33], 'led1Sample': [20170.67], 'led2Buffer': [26578.33], 'led2Sample': [12724.67]})
# new_data = pd.DataFrame({'calculatedRatio': [0.189778691], 'led1Buffer': [23209.33], 'led1Sample': [17672], 'led2Buffer': [19850.33], 'led2Sample': [10360.33]}) #SCT
new_data = pd.DataFrame({'calculatedRatio': [0.149174719], 'led1Buffer': [24122], 'led1Sample': [18368.33], 'led2Buffer': [21733.33], 'led2Sample': [9114.67]}) #Normal
predicted_result = loaded_model.predict(new_data)
print(predicted_result)