import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import pickle
import matplotlib.pyplot as plt
import seaborn as sns
import os

curdir = os.getcwd()
path_delim = '/'
data = pd.read_csv(curdir + path_delim + 'data/bquxjob_6ffc1cff_18c02a130c1.csv')
data = data.dropna()
print(data)

data.plot()

label_encoder = LabelEncoder()
categorical_cols = [] #['deviceId', 'deviceSerialNumber', 'classificationResult']
for col in categorical_cols:
    data[col] = label_encoder.fit_transform(data[col])

X = data[['calculatedRatio', 'deviceRatio', 'led1Buffer', 'led2Buffer', 'led1Sample', 'led2Sample']] #, 'deviceId', 'deviceSerialNumber']]
y = data['classificationResult']

print(X)
print(y)

# Fit the LabelEncoder on the entire column
# label_encoder.fit(data['classificationResult'])

with open('label_encoder.pkl', 'wb') as label_encoder_file:
    pickle.dump(label_encoder, label_encoder_file)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = GaussianNB()
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)

confusion = confusion_matrix(y_test, y_pred)

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)

with open('gaussian_naive_bayes_model.pkl', 'wb') as model_file:
    pickle.dump(model, model_file)

with open('label_encoder.pkl', 'rb') as label_encoder_file:
    loaded_label_encoder = pickle.load(label_encoder_file)
# print(loaded_label_encoder.classes_)
# print(loaded_label_encoder.label)

with open('gaussian_naive_bayes_model.pkl', 'rb') as model_file:
    loaded_model = pickle.load(model_file)

# loaded_label_encoder = label_encoder
# loaded_model = model 

# new_data = pd.DataFrame({'calculatedRatio': label_encoder.fit_transform([0.126976079]), 'led1Buffer': label_encoder.fit_transform([24313.67]), 'led1Sample': label_encoder.fit_transform([20531]), 'led2Buffer': label_encoder.fit_transform([26565]), 'led2Sample': label_encoder.fit_transform([9975.33])})
# new_data = pd.DataFrame({'calculatedRatio': loaded_label_encoder.fit_transform([0.17500836]), 'led1Buffer': loaded_label_encoder.fit_transform([24843.33]), 'led1Sample': loaded_label_encoder.fit_transform([19678]), 'led2Buffer': loaded_label_encoder.fit_transform([26715.33]), 'led2Sample': loaded_label_encoder.fit_transform([13842.67])})
# new_data = pd.DataFrame({'calculatedRatio': loaded_label_encoder.fit_transform([0.175881142]), 'led1Buffer': loaded_label_encoder.fit_transform([24256]), 'led1Sample': loaded_label_encoder.fit_transform([16303]), 'led2Buffer': loaded_label_encoder.fit_transform([27016.33]), 'led2Sample': loaded_label_encoder.fit_transform([4612.67])})
# new_data = pd.DataFrame({'calculatedRatio': loaded_label_encoder.fit_transform([0.126976079]), 'led1Buffer': loaded_label_encoder.fit_transform([24313.67]), 'led1Sample': loaded_label_encoder.fit_transform([20531]), 'led2Buffer': loaded_label_encoder.fit_transform([26565]), 'led2Sample': loaded_label_encoder.fit_transform([9975.33])})
new_data = pd.DataFrame({'calculatedRatio': 0.231057205, 'deviceRatio': 0.231057205,'led1Buffer': 23776.33, 'led2Buffer': 26401.67, 
            'led1Sample': 16286, 'led2Sample': 6952.67}, index=[0])
# new_data = pd.DataFrame({
#     'calculatedRatio': [0.175881142],
#     'led1Buffer': [24256],
#     'led1Sample': [16303],
#     'led2Buffer': [27016.33],
#     'led2Sample': [4612.67]
# })
print(new_data)

# new_data = new_data.apply(lambda col: loaded_label_encoder.transform(col))
predicted_result = loaded_model.predict(new_data)
print(predicted_result.item())

X_test_encoded = X_test.copy()
for col in categorical_cols:
    X_test_encoded[col] = loaded_label_encoder.transform(X_test[col])

print(X_test_encoded)

y_pred = model.predict(X_test_encoded)
print(pd.Series(y_pred).describe())