![[PukiWiki]](image/pukiwiki.png "[PukiWiki]")
#!/home/rtheta/.pyenv/shims/python
# -*- coding: utf-8 -*-
import sys sys.path.append("/home/rtheta/.local/lib/python3.8/site-packages/") import pandas as pd import numpy as np import json import cgi from sklearn import linear_model
print("Content-type: application/json") print("\n\n")
data = sys.stdin.read() wine_df = pd.read_json(data)
#wineをjsonからcsvに変換
#wine_df.to_csv('/home/rtheta/kaiki/123456.csv', header=False, index=False) new_wine_df=wine_df[4:]
#test=wine_df.iloc[0].values
# sklearn.linear_model.LinearRegression クラスを読み込み clf = linear_model.LinearRegression()
# 説明変数 X = new_wine_df.iloc[:, [7]].values
# 目的変数 Y = new_wine_df[10].values
# 予測モデルを作成 clf.fit(X, Y)
# 回帰係数
#print(clf.coef_) a = clf.coef_[0]
# 切片 (誤差)
#print(clf.intercept_) b = clf.intercept_
# 決定係数
#print(clf.score(X, Y)) c = clf.score(X, Y)
#予測値(list) d=clf.predict(X)
predict_list = ["", "", "予測値", "float"] predict_list.extend(d) wine_df[new_wine_df.iloc[0, :].size]=pd.DataFrame(predict_list)
result = {"回帰係数":a,"切片":b,"決定係数":c}
#result = {"0":{"0":"回帰係数","1":a},"1":{"0":"切片","1":b},"2":{"0":"決定係数","1":c}}
#print(json.JSONEncoder().encode(result)+wine_df.T.to_json()) print(wine_df.T.to_json())
#print(json.JSONEncoder().encode(result))
print('\n')
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4927234/
https://www.jstage.jst.go.jp/article/qes/4/3/4_3/_article/-char/ja
https://www.jstage.jst.go.jp/result/global/-char/ja?languageKind=ja&item1=8&word1=%E7%94%B0%E5%8F%A3+%E7%8E%84%E4%B8%80&yearfrom=&cond1=2&translate=0&yearto=&bglobalSearch=false&fromPage=/search/global/_search/-char/ja
https://www.heisei-u.ac.jp/ba/fukui/pdf/analysis34.pdf
https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/106108/1/0285-2.pdf
http://train.gomi.info/oatable/
| 月曜日 | 火曜日 | 水曜日 | 木曜日 | 金曜日 | |
| 1-2 | 研究会 | ||||
| 3-4 | |||||
| 5-6 | |||||
| 7-8 | |||||
| 9-10 | |||||
| 11-14 | 予備日 |
実験１に必要なファイル
#ref(): File not found: "sample.ino" at page "横井_backup"
sensa.py