Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit06f57a2

Browse files
committed
add kfold cross validation tutorial
1 parent4150ce8 commit06f57a2

File tree

5 files changed

+181
-0
lines changed

5 files changed

+181
-0
lines changed

‎README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -90,6 +90,7 @@ This is a repository of all the tutorials of [The Python Code](https://www.thepy
9090
-[Handling Imbalanced Datasets: A Case Study with Customer Churn](https://www.thepythoncode.com/article/handling-imbalanced-datasets-sklearn-in-python). ([code](machine-learning/handling-inbalance-churn-data))
9191
-[Logistic Regression using PyTorch in Python](https://www.thepythoncode.com/article/logistic-regression-using-pytorch). ([code](machine-learning/logistic-regression-in-pytorch))
9292
-[Dropout Regularization using PyTorch in Python](https://www.thepythoncode.com/article/dropout-regularization-in-pytorch). ([code](machine-learning/dropout-in-pytorch))
93+
-[K-Fold Cross Validation using Scikit-Learn in Python](https://www.thepythoncode.com/article/kfold-cross-validation-using-sklearn-in-python). ([code](machine-learning/k-fold-cross-validation-sklearn))
9394

9495
-###[General Python Topics](https://www.thepythoncode.com/topic/general-python-topics)
9596
-[How to Make Facebook Messenger bot in Python](https://www.thepythoncode.com/article/make-bot-fbchat-python). ([code](general/messenger-bot))
Lines changed: 133 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,133 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type":"code",
5+
"execution_count":2,
6+
"metadata": {
7+
"id":"cLkNm1Ywb3Eh"
8+
},
9+
"outputs": [],
10+
"source": [
11+
"# Load libraries\n",
12+
"from sklearn import datasets\n",
13+
"from sklearn import metrics\n",
14+
"from sklearn.model_selection import KFold, cross_val_score\n",
15+
"from sklearn.pipeline import make_pipeline\n",
16+
"from sklearn.linear_model import LogisticRegression\n",
17+
"from sklearn.preprocessing import StandardScaler"
18+
]
19+
},
20+
{
21+
"cell_type":"code",
22+
"execution_count":3,
23+
"metadata": {
24+
"id":"TvR-6-N55ZGJ"
25+
},
26+
"outputs": [],
27+
"source": [
28+
"# digits dataset loading\n",
29+
"digits = datasets.load_digits()\n",
30+
"# Create features matrix\n",
31+
"features = digits.data\n",
32+
"# Create target vector\n",
33+
"target = digits.target"
34+
]
35+
},
36+
{
37+
"cell_type":"code",
38+
"execution_count":7,
39+
"metadata": {
40+
"id":"zlsG8vbu5cqh"
41+
},
42+
"outputs": [],
43+
"source": [
44+
"# standardization\n",
45+
"standard_scaler = StandardScaler()\n",
46+
"# logistic regression creation\n",
47+
"logit = LogisticRegression()"
48+
]
49+
},
50+
{
51+
"cell_type":"code",
52+
"execution_count":8,
53+
"metadata": {
54+
"colab": {
55+
"base_uri":"https://localhost:8080/"
56+
},
57+
"id":"4LcbDlYC5m-E",
58+
"outputId":"dc10db6a-272d-4a37-d083-758b4a83dcfb"
59+
},
60+
"outputs": [
61+
{
62+
"data": {
63+
"text/plain": [
64+
"array([0.92682927, 0.98170732, 0.95731707, 0.95121951, 0.98159509,\n",
65+
" 0.97546012, 0.98159509, 0.98773006, 0.96319018, 0.97546012,\n",
66+
" 0.96932515])"
67+
]
68+
},
69+
"execution_count":8,
70+
"metadata": {},
71+
"output_type":"execute_result"
72+
}
73+
],
74+
"source": [
75+
"# pipeline creation for standardization and performing logistic regression\n",
76+
"pipeline = make_pipeline(standard_scaler, logit)\n",
77+
"# perform k-Fold cross-validation\n",
78+
"kf = KFold(n_splits=11, shuffle=True, random_state=2)\n",
79+
"# k-fold cross-validation conduction\n",
80+
"cv_results = cross_val_score(pipeline, # Pipeline\n",
81+
" features, # Feature matrix\n",
82+
" target, # Target vector\n",
83+
" cv=kf, # Cross-validation technique\n",
84+
" scoring=\"accuracy\", # Loss function\n",
85+
" n_jobs=-1) # Use all CPU cores\n",
86+
"# View score for all 11 folds\n",
87+
"cv_results"
88+
]
89+
},
90+
{
91+
"cell_type":"code",
92+
"execution_count":9,
93+
"metadata": {
94+
"colab": {
95+
"base_uri":"https://localhost:8080/"
96+
},
97+
"id":"hdX0sbfBaWsI",
98+
"outputId":"9fdc89ce-c2f7-432d-8c6a-35a65f751066"
99+
},
100+
"outputs": [
101+
{
102+
"data": {
103+
"text/plain": [
104+
"0.968311727177506"
105+
]
106+
},
107+
"execution_count":9,
108+
"metadata": {},
109+
"output_type":"execute_result"
110+
}
111+
],
112+
"source": [
113+
"# Calculate mean\n",
114+
"cv_results.mean()"
115+
]
116+
}
117+
],
118+
"metadata": {
119+
"colab": {
120+
"name":"CrossValidation-ScikitLearn_PythonCodeTutorial.ipynb",
121+
"provenance": []
122+
},
123+
"kernelspec": {
124+
"display_name":"Python 3",
125+
"name":"python3"
126+
},
127+
"language_info": {
128+
"name":"python"
129+
}
130+
},
131+
"nbformat":4,
132+
"nbformat_minor":0
133+
}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
#[K-Fold Cross Validation using Scikit-Learn in Python](https://www.thepythoncode.com/article/kfold-cross-validation-using-sklearn-in-python)
Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
# -*- coding: utf-8 -*-
2+
"""CrossValidation-ScikitLearn_PythonCodeTutorial.ipynb
3+
4+
Automatically generated by Colaboratory.
5+
6+
Original file is located at
7+
https://colab.research.google.com/drive/15FFmKBlvdAFCP4-Ka2SoFsWC93PjdxJH
8+
"""
9+
10+
# Load libraries
11+
fromsklearnimportdatasets
12+
fromsklearnimportmetrics
13+
fromsklearn.model_selectionimportKFold,cross_val_score
14+
fromsklearn.pipelineimportmake_pipeline
15+
fromsklearn.linear_modelimportLogisticRegression
16+
fromsklearn.preprocessingimportStandardScaler
17+
18+
# digits dataset loading
19+
digits=datasets.load_digits()
20+
# Create features matrix
21+
features=digits.data
22+
# Create target vector
23+
target=digits.target
24+
25+
# standardization
26+
standard_scaler=StandardScaler()
27+
# logistic regression creation
28+
logit=LogisticRegression()
29+
30+
# pipeline creation for standardization and performing logistic regression
31+
pipeline=make_pipeline(standard_scaler,logit)
32+
# perform k-Fold cross-validation
33+
kf=KFold(n_splits=11,shuffle=True,random_state=2)
34+
# k-fold cross-validation conduction
35+
cv_results=cross_val_score(pipeline,# Pipeline
36+
features,# Feature matrix
37+
target,# Target vector
38+
cv=kf,# Cross-validation technique
39+
scoring="accuracy",# Loss function
40+
n_jobs=-1)# Use all CPU cores
41+
# View score for all 11 folds
42+
cv_results
43+
44+
# Calculate mean
45+
cv_results.mean()
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
scikit-learn

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp