“Tous les algorithim de classification se comparent” Réponses codées

Tous les algorithim de classification se comparent

#Importing basic packages
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

#Importing sklearn modules
from sklearn.metrics import mean_squared_error,confusion_matrix, precision_score, recall_score, auc,roc_curve
from sklearn import ensemble, linear_model, neighbors, svm, tree, neural_network
from sklearn.linear_model import Ridge
from sklearn.preprocessing import PolynomialFeatures
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.pipeline import make_pipeline
from sklearn import svm,model_selection, tree, linear_model, neighbors, naive_bayes, ensemble, discriminant_analysis, gaussian_process
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

# Splitting train and split data
x_train, x_test, y_train, y_test=train_test_split(x,y,test_size=0.2, random_state=0)

# Application of all Machine Learning methods
models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))

# evaluate each model in turn
results = []
names = []
scoring = 'accuracy'
for name, model in models:
	kfold = model_selection.KFold(n_splits=10, random_state=seed)
	cv_results = model_selection.cross_val_score(model, x_train, y_train, cv=kfold, scoring=scoring)
	results.append(cv_results)
	names.append(name)
	msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
	print(msg)
# boxplot algorithm comparison
fig = plt.figure()
fig.suptitle('Comparison between different MLAs')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()

# Application of all Machine Learning methods
MLA = [
    #GLM
    linear_model.LogisticRegressionCV(),
    linear_model.PassiveAggressiveClassifier(),
    linear_model. RidgeClassifierCV(),
    linear_model.SGDClassifier(),
    linear_model.Perceptron(),
    
    #Ensemble Methods
    ensemble.AdaBoostClassifier(),
    ensemble.BaggingClassifier(),
    ensemble.ExtraTreesClassifier(),
    ensemble.GradientBoostingClassifier(),
    ensemble.RandomForestClassifier(),

    #Gaussian Processes
    gaussian_process.GaussianProcessClassifier(),
    
    #SVM
    svm.SVC(probability=True),
    svm.NuSVC(probability=True),
    svm.LinearSVC(),
    
    #Trees    
    tree.DecisionTreeClassifier(),
  
    #Navies Bayes
    naive_bayes.BernoulliNB(),
    naive_bayes.GaussianNB(),
    
    #Nearest Neighbor
    neighbors.KNeighborsClassifier(),
    ]


MLA_columns = []
MLA_compare = pd.DataFrame(columns = MLA_columns)

row_index = 0
for alg in MLA:  
    
    predicted = alg.fit(x_train, y_train).predict(x_test)
    fp, tp, th = roc_curve(y_test, predicted)
    MLA_name = alg.__class__.__name__
    MLA_compare.loc[row_index,'MLA used'] = MLA_name
    MLA_compare.loc[row_index, 'Train Accuracy'] = round(alg.score(x_train, y_train), 4)
    MLA_compare.loc[row_index, 'Test Accuracy'] = round(alg.score(x_test, y_test), 4)
    MLA_compare.loc[row_index, 'Precission'] = precision_score(y_test, predicted)
    MLA_compare.loc[row_index, 'Recall'] = recall_score(y_test, predicted)
    MLA_compare.loc[row_index, 'AUC'] = auc(fp, tp)

    row_index+=1
    
MLA_compare.sort_values(by = ['MLA Test Accuracy'], ascending = False, inplace = True)    
MLA_compare

# Creating plot to show the train accuracy
plt.subplots(figsize=(13,5))
sns.barplot(x="MLA used", y="Train Accuracy",data=MLA_compare,palette='hot',edgecolor=sns.color_palette('dark',7))
plt.xticks(rotation=90)
plt.title('MLA Train Accuracy Comparison')
plt.show()

# Creating plot to show the test accuracy
plt.subplots(figsize=(13,5))
sns.barplot(x="MLA used", y="Test Accuracy",data=MLA_compare,palette='hot',edgecolor=sns.color_palette('dark',7))
plt.xticks(rotation=90)
plt.title('Accuraccy of different machine learning models')
plt.show()

# Creating plots to compare precission of the MLAs
plt.subplots(figsize=(13,5))
sns.barplot(x="MLA used", y="Precission",data=MLA_compare,palette='hot',edgecolor=sns.color_palette('dark',7))
plt.xticks(rotation=90)
plt.title('Comparing different Machine Learning Models')
plt.show()

https://dibyendudeb.com/comparing-machine-learning-algorithms/