빅데이터 분석기사 실기

• Pima Indians Diabetes (피마 인디언 당뇨병)

import pandas as pd
import sklearn

help(sklearn)

import sklearn.ensemble
dir(sklearn.ensemble) # 확인

from sklearn.ensemble import RandomForestClassifier
X_train.head().T
X_train.info()

X_train.describe()
X_train.isnull().sum()
X_test.isnull().sum()

help(df.drop)
X_train.drop('id', axis=1, inplace=True)
X_test.drop('id', axis=1, inplace=True)

X_train.info()

help(RandomForestClassifier)

model = RandomForestClassifier()
model.fit(X_train, y_train['Outcome'])
predictions = model.predict(X_test)
round(model.score(X_train, y_train['Outcome']) * 100, 2)

output.to_csv('123456.csv', index=False)