106 lines (72 with data), 2.9 kB

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Feb  3 09:37:21 2023

@author: ming
"""

import pandas as pd
from fancyimpute import KNN
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report,confusion_matrix
from sklearn import preprocessing

from sklearn.metrics import roc_auc_score
from sklearn.model_selection import GridSearchCV


#load data
X=pd.read_csv(r"/Users/ming/Downloads/Xset1.csv")
Y=pd.read_csv(r"/Users/ming/Downloads/Y.csv")

#del columns
X.dropna(thresh=100)

#impute
Xc=X.columns

X = pd.DataFrame(KNN(k=6).fit_transform(X)) 
X.columns=Xc

#standardize
standardized_X = preprocessing.scale(X)

#oversampling

#imblearn进行随机过采样
from imblearn.over_sampling import RandomOverSampler
ros = RandomOverSampler(random_state=0)
X_resampled, y_resampled = ros.fit_resample(standardized_X, Y)


models = {
    "knn": KNeighborsClassifier(n_neighbors=1),
    "naive_bayes": GaussianNB(),
    "logit": LogisticRegression(solver="lbfgs", multi_class="auto"),
    "svm": SVC(kernel="rbf", gamma="auto"),
    "decision_tree": DecisionTreeClassifier(criterion='gini',splitter='random',max_depth=15,min_samples_leaf=10,min_samples_split=10), 
    "random_forest": RandomForestClassifier(n_estimators=60,max_depth=6,max_samples=70,max_features=5),
    "mlp": MLPClassifier()
}

trainX, testX, trainY, testY = train_test_split(X_resampled, y_resampled, random_state=3, test_size=0.2)

print("use '{}' bulid model...".format("random_forest"))
model = models["random_forest"]
model.fit(trainX, trainY)

'''
tree_param_grid = {'n_estimators': range(50,100,10),
                  'min_samples_split':range(30,111,20),
                  'max_features':range(5,76,10),
                  'max_depth':range(3,22,3)
                  }
 
tree_best = GridSearchCV(model,param_grid = tree_param_grid,cv = 3,scoring="roc_auc",n_jobs= -1, verbose = 100) 
#Gridsearch turning parameters  
tree_best.fit(trainX, trainY)

print(tree_best.best_estimator_)
print(tree_best.best_params_,"  ","得分：",tree_best.best_score_)
'''

features_importance = pd.concat([pd.DataFrame(Xc).T,pd.DataFrame(model.feature_importances_).T],axis=0).T
features_importance.columns=["feature","importance"]

## prediction
print("elvaluation...")
predictions = model.predict(testX)
print(classification_report(testY, predictions))
auc_score = roc_auc_score(testY, predictions)
print('CONFUSION MATRIX')
print(confusion_matrix(testY, predictions))
print("AUC")
print(auc_score)