Python - Grid Search Hyper parameter

'''

지금까지 왜 BOOSTING이 BAGGING에 밀렸는가 ?

너무 많은 계산량

튜닝해야 할 파라미터가 너무 많다

bagging -> 분산 컴퓨팅 기능

boosting -> 분산 컴퓨팅 어려움

- loss

- learning_rate

- n_estimators

- subsample

'''

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn.preprocessing import LabelEncoder

from sklearn.model_selection import train_test_split, GridSearchCV

from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier

from sklearn.ensemble import BaggingClassifier

from sklearn.ensemble import ExtraTreesClassifier

from sklearn.neighbors import KNeighborsClassifier

from sklearn.linear_model import LogisticRegression

from sklearn.svm import SVC

from sklearn.ensemble import VotingClassifier

from sklearn.model_selection import GridSearchCV

from sklearn.metrics import mean_squared_error

from sklearn.tree import plot_tree

from sklearn import metrics

import warnings

warnings.filterwarnings('ignore')

df = pd.read_csv('./titanic/train.csv')

df_kg = pd.read_csv('./titanic/test.csv')

df1 = df.copy()

df1.set_index('PassengerId', inplace=True)

df_kg.set_index('PassengerId', inplace=True)

df1.drop(['Name'], axis=1, inplace=True)

df_kg.drop(['Name'], axis=1, inplace=True)

df_kg.Cabin.astype(str)

# 결측치 처리

df1.Cabin.fillna('N', inplace=True)

df1.Embarked.fillna('S', inplace=True)

df1.Age.fillna(df1.Age.median(), inplace=True)

df_kg.Cabin.fillna('N', inplace=True)

df_kg.Fare.fillna(df1.Fare.median(), inplace=True)

df_kg.Age.fillna(df1.Age.median(), inplace=True)

df1.Cabin = df1.Cabin.apply(lambda x:x[0])

df_kg.Cabin = df_kg.Cabin.apply(lambda x:x[0])

# 인코딩

og_columns = df1.columns[(df1.dtypes=='O')|(df1.dtypes=='category')|(df1.dtypes=='bool')]

for i in og_columns:

    globals()[f'df1_{i}_encoder'] = LabelEncoder()

    globals()[f'df1_{i}_encoder'].fit(df1[i])

    globals()[f'df_kg_{i}_encoder'] = LabelEncoder()

    globals()[f'df_kg_{i}_encoder'].fit(df_kg[i])

    df1[i] = globals()[f'df1_{i}_encoder'].transform(df1[i])

    df_kg[i] = globals()[f'df_kg_{i}_encoder'].transform(df_kg[i])

# X, y 분리

X = df1.drop('Survived', axis=1)

y = df1.Survived

# train, test 분리

X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.1, random_state=19 )

parameters = {

    'n_estimators':[100,200,300],

    'random_state':[0,10,20,30],

    'max_depth':[1,3,5,7,9],

    'min_samples_split':[5,10],

    'criterion':['gini','entropy']

}

params = {

   

    'n_estimators':[50,100,200,300],

    'learning_rate':[0.05,1,2,3]

}

#{'criterion': 'entropy', 'max_depth': 9, 'min_samples_split': 10, 'n_estimators': 200, 'random_state': 20}

rd_clf = RandomForestClassifier()

rd_clf.fit(X_train, y_train)

print(rd_clf.score(X_val, y_val))

gvm_clf = GradientBoostingClassifier()

gvm_clf.fit(X_train, y_train)

print('gvm',gvm_clf.score(X_val, y_val))

grid_dt = GridSearchCV(gvm_clf,  param_grid=params ,cv = 5, n_jobs = -1)

grid_dt.fit(X_train,y_train)

print(grid_dt.best_params_)

print(grid_dt.best_estimator_.score(X_train, y_train))

rd_dt = GridSearchCV(rd_clf,  param_grid=parameters ,cv = 5, n_jobs = -1)

rd_dt.fit(X_train,y_train)

print(rd_dt.best_params_)

print(rd_dt.best_estimator_.score(X_train, y_train))

grid_dt.fit(X, y)

kg_up = df_kg.copy()

kg_up['Survived'] = grid_dt.predict(df_kg)

kg_up.Survived.to_csv('kaggle_upload_Grid3.csv')

rd_clf.fit(X, y)

kg_up = df_kg.copy()

kg_up['Survived'] = rd_clf.predict(df_kg)

kg_up.Survived.to_csv('kaggle_upload_rd_clf.csv')