Libraries and functions

from imblearn.over_sampling import SMOTE
from imblearn.pipeline import Pipeline as ImbPipeline
from scipy.stats import chi2_contingency
from sklearn.compose import ColumnTransformer
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report
from sklearn.metrics import confusion_matrix	
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder,OrdinalEncoder,MinMaxScaler
from sklearn.tree import DecisionTreeClassifier
from statsmodels.tsa.seasonal import seasonal_decompose
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.calibration import CalibratedClassifierCV

# Calculando a matriz de confusão
def conf_matrix(y_test,y_pred):
        
    conf_matrix = confusion_matrix(y_test, y_pred)
    
    conf_matrix = conf_matrix.astype('float') / conf_matrix.sum(axis=1)[:, np.newaxis] * 100
    
    # Plotando a matriz de confusão
    plt.imshow(conf_matrix, cmap='Blues', interpolation='nearest')
    plt.colorbar()
    
    # Adicionando rótulos aos eixos
    plt.title('Matriz de Confusão')
    plt.xlabel('Previsto')
    plt.ylabel('Verdadeiro')
    tick_marks = [0, 1]
    plt.xticks(tick_marks, ['Não é fraude', 'Fraude'])
    plt.yticks(tick_marks, ['Não é fraude', 'Fraude'])
    
    # Adicionando os valores na matriz
    for i in range(len(conf_matrix)):
        for j in range(len(conf_matrix[i])):
            plt.text(j, i, str(conf_matrix[i][j]), ha='center', va='center', color='black')
    
    # Exibindo a matriz de confusão
    plt.show()

Frame the Problem and Look at the Big Picture

Get the data

df=pd.read_csv('dados.csv')
df.head()
df.info()

Explore the data

(194/150000)*100
df.info()

a

df['a'].value_counts()
df['a'].hist()