機械学習　ランダムフォレスト　ワイン

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report

#データ読み込み
wine = pd.read_csv("winequality-white.csv", sep=";", encoding="utf-8")

#データをラベルとデータに分離
y = wine["quality"]
x = wine.drop("quality", axis=1)

#学習用とテスト用に分離
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)

#学習する
model = RandomForestClassifier()
model.fit(x_train, y_train)

#評価する
y_pred = model.predict(x_test)
print(classification_report(y_test, y_pred))
print("正解率 = ", accuracy_score(y_test, y_pred))

precision    recall  f1-score   support

           3       0.00      0.00      0.00         2
           4       0.62      0.17      0.27        29
           5       0.64      0.67      0.65       275
           6       0.65      0.75      0.70       468
           7       0.68      0.54      0.60       168
           8       0.87      0.36      0.51        36
           9       0.00      0.00      0.00         2

    accuracy                           0.66       980
   macro avg       0.50      0.36      0.39       980
weighted avg       0.66      0.66      0.65       980

正解率 =  0.6581632653061225

import matplotlib.pyplot as plt
import pandas as pd

#ワインデータの読み込み
wine = pd.read_csv("winequality-white.csv", sep=";", encoding="utf-8")

#品質データごとにグループ分けして、その数を数える
count_data = wine.groupby('quality')["quality"].count()
print(count_data)

#数えたデータをグラフに描画
count_data.plot()
plt.savefig("wine-count-plt.png")
plt.show()

quality
3      20
4     163
5    1457
6    2198
7     880
8     175
9       5
Name: quality, dtype: int64

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report

#データ読み込み
wine = pd.read_csv("winequality-white.csv", sep=";", encoding="utf-8")

#データをラベルとデータに分離
y = wine["quality"]
x = wine.drop("quality", axis=1)


#yのラベルをつけ直す
newlist = []
for v in list(y):
    if v <= 4:
        newlist += [0]
    elif v <= 7:
        newlist += [1]
    else:
        newlist += [2]
y = newlist            

#学習用とテスト用に分離
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)

#学習する
model = RandomForestClassifier()
model.fit(x_train, y_train)

#評価する
y_pred = model.predict(x_test)
print(classification_report(y_test, y_pred))
print("正解率 = ", accuracy_score(y_test, y_pred))

precision    recall  f1-score   support

           0       0.50      0.12      0.19        42
           1       0.94      0.99      0.96       900
           2       1.00      0.37      0.54        38

    accuracy                           0.93       980
   macro avg       0.81      0.49      0.57       980
weighted avg       0.92      0.93      0.91       980

正解率 =  0.9326530612244898