機器學(xué)習(xí)實戰(zhàn)-決策樹-葉子分類

import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as pltfrom sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifier from sklearn.model_selection import GridSearchCV train = pd.read_csv('train.csv')

train.head()

train.shape

# 葉子類別數(shù) len(train.species.unique())

Data Preparation

# 把字符串類別轉(zhuǎn)化為數(shù)字形式 lb = LabelEncoder().fit(train.species) labels = lb.transform(train.species) # 去掉'species', 'id'的列 data = train.drop(['species', 'id'], axis=1) data.head()

# 切分?jǐn)?shù)據(jù)集 x_train,x_test,y_train,y_test = train_test_split(data, labels, test_size=0.3, stratify=labels)

建模分析

tree = DecisionTreeClassifier() tree.fit(x_train, y_train)

模型優(yōu)化

# max_depth:樹的最大深度 # min_samples_split:內(nèi)部節(jié)點再劃分所需最小樣本數(shù) # min_samples_leaf:葉子節(jié)點最少樣本數(shù) param_grid = {'max_depth': [30,40,50,60,70],'min_samples_split': [2,3,4,5,6],'min_samples_leaf':[1,2,3,4]} # 網(wǎng)格搜索 model = GridSearchCV(DecisionTreeClassifier(), param_grid, cv=3) model.fit(x_train, y_train) print(model.best_estimator_)

model.score(x_train, y_train)

model.score(x_test, y_test)

決策樹-動物分類

import pandas as pd import numpy as np # pip install missingno import missingno as msno import seaborn as sns import matplotlib.pyplot as plt from sklearn.tree import DecisionTreeClassifier from sklearn.model_selection import GridSearchCV data = pd.read_csv('zoo.csv') data.head()

# 查看數(shù)據(jù)形狀 data.shape

# 查看數(shù)據(jù)類型分布 data.dtypes

data.describe()

# 查看數(shù)據(jù)缺失情況 p=msno.bar(data)

# 畫熱力圖，數(shù)值為兩個變量之間的相關(guān)系數(shù) plt.figure(figsize=(20,20)) p=sns.heatmap(data.corr(), annot=True, annot_kws = { 'fontsize' : 15 },square=True)

# 查看類別分布 pd.value_counts(data["class_type"])

# 獲取訓(xùn)練數(shù)據(jù)和標(biāo)簽 x_data = data.drop(['animal_name', 'class_type'], axis=1) y_data = data['class_type'] from sklearn.model_selection import train_test_split # 切分?jǐn)?shù)據(jù)集，stratify=y表示切分后訓(xùn)練集和測試集中的數(shù)據(jù)類型的比例跟切分前y中的比例一致 # 比如切分前y中0和1的比例為1:2，切分后y_train和y_test中0和1的比例也都是1:2 x_train,x_test,y_train,y_test = train_test_split(x_data, y_data, test_size=0.3, stratify=y_data) tree = DecisionTreeClassifier() tree.fit(x_train, y_train)

tree.score(x_test, y_test)

模型優(yōu)化

param_grid = {'max_depth': [5,10,15,20,25],'min_samples_split': [2,3,4,5,6],'min_samples_leaf':[1,2,3,4]} model = GridSearchCV(DecisionTreeClassifier(), param_grid, cv=3, iid=True) model.fit(x_train, y_train) print(model.best_estimator_)

model.score(x_test, y_test)

param_grid = {'max_depth': [8,9,10,11,12],'min_samples_split': [2,3,4,5,6],'min_samples_leaf':[1,2,3,4]} model2 = GridSearchCV(DecisionTreeClassifier(), param_grid, cv=3, iid=True) model2.fit(x_train, y_train) print(model2.best_estimator_)

總結(jié)

以上是生活随笔為你收集整理的机器学习实战-决策树-22的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。