COMP7404 Machine Learing——Confusion Matrix & Precision/Recall/F1

最新推荐文章于 2024-11-06 11:32:21 发布

hxxjxw

最新推荐文章于 2024-11-06 11:32:21 发布

阅读量176

点赞数

文章标签：机器学习

本文链接：https://blog.csdn.net/hxxjxw/article/details/110095627

版权

本文介绍了使用Sklearn进行乳腺癌数据预处理、模型训练（SVM与标准化），通过混淆矩阵展示预测结果，并计算了精确率、召回率和F1分数。最后，展示了如何在GridSearchCV中使用Scoring Metric优化SVM参数。

摘要由CSDN通过智能技术生成

Confusion Matrix

import pandas as pd
import numpy as np
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import cross_val_score
pipe_svc = make_pipeline(StandardScaler(), SVC(random_state=1))

from sklearn.metrics import confusion_matrix
pipe_svc.fit(X_train, y_train)
y_pred = pipe_svc.predict(X_test)
confmat = confusion_matrix(y_true=y_test, y_pred=y_pred)
print(confmat)

如果想要改变位置

confmat = confusion_matrix(y_true=y_test, y_pred=y_pred, labels=[1, 0])

import pandas as pd
import numpy as np
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import cross_val_score
pipe_svc = make_pipeline(StandardScaler(), SVC(random_state=1))

from sklearn.metrics import confusion_matrix
pipe_svc.fit(X_train, y_train)
y_pred = pipe_svc.predict(X_test)
confmat = confusion_matrix(y_true=y_test, y_pred=y_pred)
print(confmat)

import matplotlib.pyplot as plt
fig, ax = plt.subplots(figsize=(2.5, 2.5))
ax.matshow(confmat, cmap=plt.cm.Blues, alpha=0.3)
for i in range(confmat.shape[0]):
    for j in range(confmat.shape[1]):
        ax.text(x=j, y=i, s=confmat[i, j], va='center', ha='center')
plt.xlabel('Predicted label')
plt.ylabel('True label')
plt.tight_layout()
plt.show()

Precision/Recall/F1

import pandas as pd
import numpy as np
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import cross_val_score
pipe_svc = make_pipeline(StandardScaler(), SVC(random_state=1))

from sklearn.metrics import confusion_matrix
pipe_svc.fit(X_train, y_train)
y_pred = pipe_svc.predict(X_test)

from sklearn.metrics import precision_score, recall_score, f1_score
print('Precision: %.3f' % precision_score(y_true=y_test, y_pred=y_pred))
print('Recall: %.3f' % recall_score(y_true=y_test, y_pred=y_pred))
print('F1: %.3f' % f1_score(y_true=y_test, y_pred=y_pred))

Scoring Metric(Precision/Recall/F1) in GridSearchCV

import pandas as pd
import numpy as np
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import cross_val_score
pipe_svc = make_pipeline(StandardScaler(), SVC(random_state=1))

from sklearn.metrics import confusion_matrix
pipe_svc.fit(X_train, y_train)

from sklearn.metrics import make_scorer
from sklearn.metrics import precision_score, recall_score, f1_score
scorer = make_scorer(f1_score, pos_label=0)
c_gamma_range = [0.01, 0.1, 1.0, 10.0]
param_grid = [{'svc__C': c_gamma_range, 'svc__kernel': ['linear']},
              {'svc__C': c_gamma_range, 'svc__gamma': c_gamma_range, 'svc__kernel': ['rbf']}]
gs = GridSearchCV(estimator=pipe_svc, param_grid=param_grid, scoring=scorer, cv=10, n_jobs=-1)
gs = gs.fit(X_train, y_train)
print(gs.best_score_)
print(gs.best_params_)