python一些代码总结

1.绘画混淆矩阵

​import matplotlib.pyplot as plt
import itertools
def plot_confusion_matrix(cm, classes,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    """
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=0)
    plt.yticks(tick_marks, classes)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')

​from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(gender_train,genderlabel,test_size = 0.2, random_state = 0)

LR_model = LogisticRegression()

LR_model.fit(X_train,y_train)
y_pred = LR_model.predict(X_test)
print (LR_model.score(X_test,y_test))

cnf_matrix = confusion_matrix(y_test,y_pred)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

print("accuracy metric in the testing dataset: ", (cnf_matrix[1,1]+cnf_matrix[0,0])/(cnf_matrix[0,0]+cnf_matrix[1,1]+cnf_matrix[1,0]+cnf_matrix[0,1]))

# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Gender-Confusion matrix')
plt.show()

2.网格搜索

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.tree import DecisionTreeRegressor              
from sklearn.ensemble import AdaBoostRegressor
from sklearn.ensemble import BaggingRegressor
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.decomposition import PCA
from sklearn.linear_model import Lasso
from mlxtend.regressor import StackingCVRegressor
from xgboost import XGBRegressor
##选取grbt进行调参
param_grid = [   
    {'n_estimators': [50,100,150], 'max_features': [2, 4, 6, 8],'max_depth':[3,5,7]}
  ]

grbt_reg = GradientBoostingRegressor()
grid_search = GridSearchCV(grbt_reg, param_grid, cv=5,
                           scoring='neg_mean_squared_error', return_train_score=True)
grid_search.fit(x_train, y_train.ravel())

cvres = grid_search.cv_results_
for mean_score, params in zip(cvres["mean_test_score"], cvres["params"]):
    print(np.sqrt(-mean_score), params)
   
grid_search.best_params_

feature_importances = grid_search.best_estimator_.feature_importances_