03.random_forest_demo

最新推荐文章于 2024-04-01 11:06:31 发布

孟玄同mxy

最新推荐文章于 2024-04-01 11:06:31 发布

阅读量174

点赞数

文章标签： python

本文链接：https://blog.csdn.net/qq_44268986/article/details/120405660

版权

注：本案例为黑马的课堂案例，上传仅为方便查看

# 1.获取数据
# 2.数据基本处理
# 2.1 确定特征值,目标值
# 2.2 缺失值处理
# 2.3 数据集划分
# 3.特征工程(字典特征抽取)
# 4.机器学习(随机森林+cv)
# 5.模型评估

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.feature_extraction import DictVectorizer
# from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.ensemble import RandomForestClassifier

# 1.获取数据
data = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")

data

	row.names	pclass	survived	name	age	embarked	home.dest	room	ticket	boat	sex
0	1	1st	1	Allen, Miss Elisabeth Walton	29.0000	Southampton	St Louis, MO	B-5	24160 L221	2	female
1	2	1st	0	Allison, Miss Helen Loraine	2.0000	Southampton	Montreal, PQ / Chesterville, ON	C26	NaN	NaN	female
2	3	1st	0	Allison, Mr Hudson Joshua Creighton	30.0000	Southampton	Montreal, PQ / Chesterville, ON	C26	NaN	(135)	male
3	4	1st	0	Allison, Mrs Hudson J.C. (Bessie Waldo Daniels)	25.0000	Southampton	Montreal, PQ / Chesterville, ON	C26	NaN	NaN	female
4	5	1st	1	Allison, Master Hudson Trevor	0.9167	Southampton	Montreal, PQ / Chesterville, ON	C22	NaN	11	male
5	6	1st	1	Anderson, Mr Harry	47.0000	Southampton	New York, NY	E-12	NaN	3	male
6	7	1st	1	Andrews, Miss Kornelia Theodosia	63.0000	Southampton	Hudson, NY	D-7	13502 L77	10	female
7	8	1st	0	Andrews, Mr Thomas, jr	39.0000	Southampton	Belfast, NI	A-36	NaN	NaN	male
8	9	1st	1	Appleton, Mrs Edward Dale (Charlotte Lamson)	58.0000	Southampton	Bayside, Queens, NY	C-101	NaN	2	female
9	10	1st	0	Artagaveytia, Mr Ramon	71.0000	Cherbourg	Montevideo, Uruguay	NaN	NaN	(22)	male
10	11	1st	0	Astor, Colonel John Jacob	47.0000	Cherbourg	New York, NY	NaN	17754 L224 10s 6d	(124)	male
11	12	1st	1	Astor, Mrs John Jacob (Madeleine Talmadge Force)	19.0000	Cherbourg	New York, NY	NaN	17754 L224 10s 6d	4	female
12	13	1st	1	Aubert, Mrs Leontine Pauline	NaN	Cherbourg	Paris, France	B-35	17477 L69 6s	9	female
13	14	1st	1	Barkworth, Mr Algernon H.	NaN	Southampton	Hessle, Yorks	A-23	NaN	B	male
14	15	1st	0	Baumann, Mr John D.	NaN	Southampton	New York, NY	NaN	NaN	NaN	male
15	16	1st	1	Baxter, Mrs James (Helene DeLaudeniere Chaput)	50.0000	Cherbourg	Montreal, PQ	B-58/60	NaN	6	female
16	17	1st	0	Baxter, Mr Quigg Edmond	24.0000	Cherbourg	Montreal, PQ	B-58/60	NaN	NaN	male
17	18	1st	0	Beattie, Mr Thomson	36.0000	Cherbourg	Winnipeg, MN	C-6	NaN	NaN	male
18	19	1st	1	Beckwith, Mr Richard Leonard	37.0000	Southampton	New York, NY	D-35	NaN	5	male
19	20	1st	1	Beckwith, Mrs Richard Leonard (Sallie Monypeny)	47.0000	Southampton	New York, NY	D-35	NaN	5	female
20	21	1st	1	Behr, Mr Karl Howell	26.0000	Cherbourg	New York, NY	C-148	NaN	5	male
21	22	1st	0	Birnbaum, Mr Jakob	25.0000	Cherbourg	San Francisco, CA	NaN	NaN	(148)	male
22	23	1st	1	Bishop, Mr Dickinson H.	25.0000	Cherbourg	Dowagiac, MI	B-49	NaN	7	male
23	24	1st	1	Bishop, Mrs Dickinson H. (Helen Walton)	19.0000	Cherbourg	Dowagiac, MI	B-49	NaN	7	female
24	25	1st	1	Bjornstrm-Steffansson, Mr Mauritz Hakan	28.0000	Southampton	Stockholm, Sweden / Washington, DC	NaN		D	male
25	26	1st	0	Blackwell, Mr Stephen Weart	45.0000	Southampton	Trenton, NJ	NaN	NaN	(241)	male
26	27	1st	1	Blank, Mr Henry	39.0000	Cherbourg	Glen Ridge, NJ	A-31	NaN	7	male
27	28	1st	1	Bonnell, Miss Caroline	30.0000	Southampton	Youngstown, OH	C-7	NaN	8	female
28	29	1st	1	Bonnell, Miss Elizabeth	58.0000	Southampton	Birkdale, England Cleveland, Ohio	C-103	NaN	8	female
29	30	1st	0	Borebank, Mr John James	NaN	Southampton	London / Winnipeg, MB	D-21/2	NaN	NaN	male
...	...	...	...	...	...	...	...	...	...	...	...
1283	1284	3rd	0	Vestrom, Miss Hulda Amanda Adolfina	NaN	NaN	NaN	NaN	NaN	NaN	female
1284	1285	3rd	0	Vonk, Mr Jenko	NaN	NaN	NaN	NaN	NaN	NaN	male
1285	1286	3rd	0	Ware, Mr Frederick	NaN	NaN	NaN	NaN	NaN	NaN	male
1286	1287	3rd	0	Warren, Mr Charles William	NaN	NaN	NaN	NaN	NaN	NaN	male
1287	1288	3rd	0	Wazli, Mr Yousif	NaN	NaN	NaN	NaN	NaN	NaN	male
1288	1289	3rd	0	Webber, Mr James	NaN	NaN	NaN	NaN	NaN	NaN	male
1289	1290	3rd	1	Wennerstrom, Mr August Edvard	NaN	NaN	NaN	NaN	NaN	NaN	male
1290	1291	3rd	0	Wenzel, Mr Linhart	NaN	NaN	NaN	NaN	NaN	NaN	male
1291	1292	3rd	0	Widegren, Mr Charles Peter	NaN	NaN	NaN	NaN	NaN	NaN	male
1292	1293	3rd	0	Wiklund, Mr Jacob Alfred	NaN	NaN	NaN	NaN	NaN	NaN	male
1293	1294	3rd	1	Wilkes, Mrs Ellen	NaN	NaN	NaN	NaN	NaN	NaN	female
1294	1295	3rd	0	Willer, Mr Aaron	NaN	NaN	NaN	NaN	NaN	NaN	male
1295	1296	3rd	0	Willey, Mr Edward	NaN	NaN	NaN	NaN	NaN	NaN	male
1296	1297	3rd	0	Williams, Mr Howard Hugh	NaN	NaN	NaN	NaN	NaN	NaN	male
1297	1298	3rd	0	Williams, Mr Leslie	NaN	NaN	NaN	NaN	NaN	NaN	male
1298	1299	3rd	0	Windelov, Mr Einar	NaN	NaN	NaN	NaN	NaN	NaN	male
1299	1300	3rd	0	Wirz, Mr Albert	NaN	NaN	NaN	NaN	NaN	NaN	male
1300	1301	3rd	0	Wiseman, Mr Phillippe	NaN	NaN	NaN	NaN	NaN	NaN	male
1301	1302	3rd	0	Wittevrongel, Mr Camiel	NaN	NaN	NaN	NaN	NaN	NaN	male
1302	1303	3rd	1	Yalsevac, Mr Ivan	NaN	NaN	NaN	NaN	NaN	NaN	male
1303	1304	3rd	0	Yasbeck, Mr Antoni	NaN	NaN	NaN	NaN	NaN	NaN	male
1304	1305	3rd	1	Yasbeck, Mrs Antoni	NaN	NaN	NaN	NaN	NaN	NaN	female
1305	1306	3rd	0	Youssef, Mr Gerios	NaN	NaN	NaN	NaN	NaN	NaN	male
1306	1307	3rd	0	Zabour, Miss Hileni	NaN	NaN	NaN	NaN	NaN	NaN	female
1307	1308	3rd	0	Zabour, Miss Tamini	NaN	NaN	NaN	NaN	NaN	NaN	female
1308	1309	3rd	0	Zakarian, Mr Artun	NaN	NaN	NaN	NaN	NaN	NaN	male
1309	1310	3rd	0	Zakarian, Mr Maprieder	NaN	NaN	NaN	NaN	NaN	NaN	male
1310	1311	3rd	0	Zenn, Mr Philip	NaN	NaN	NaN	NaN	NaN	NaN	male
1311	1312	3rd	0	Zievens, Rene	NaN	NaN	NaN	NaN	NaN	NaN	female
1312	1313	3rd	0	Zimmerman, Leo	NaN	NaN	NaN	NaN	NaN	NaN	male

1313 rows × 11 columns

data.describe()

	row.names	survived	age
count	1313.000000	1313.000000	633.000000
mean	657.000000	0.341965	31.194181
std	379.174762	0.474549	14.747525
min	1.000000	0.000000	0.166700
25%	329.000000	0.000000	21.000000
50%	657.000000	0.000000	30.000000
75%	985.000000	1.000000	41.000000
max	1313.000000	1.000000	71.000000

# 2.数据基本处理
# 2.1 确定特征值,目标值
x = data[["pclass", "age", "sex"]]
x.head()

	pclass	age	sex
0	1st	29.0000	female
1	1st	2.0000	female
2	1st	30.0000	male
3	1st	25.0000	female
4	1st	0.9167	male

y = data["survived"]
y.head()

0    1
1    0
2    0
3    0
4    1
Name: survived, dtype: int64

# 2.2 缺失值处理
x["age"].fillna(value=data["age"].mean(), inplace=True)

/Users/sherwin/workspaces/ai/lib/python3.6/site-packages/pandas/core/generic.py:3660: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  self._update_inplace(new_data)

x.head()

	pclass	age	sex
0	1st	29.0000	female
1	1st	2.0000	female
2	1st	30.0000	male
3	1st	25.0000	female
4	1st	0.9167	male

# 2.3 数据集划分
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22, test_size=0.2)

# 3.特征工程(字典特征抽取)
x.head()

	pclass	age	sex
0	1st	29.0000	female
1	1st	2.0000	female
2	1st	30.0000	male
3	1st	25.0000	female
4	1st	0.9167	male

x_train = x_train.to_dict(orient="records")
x_test = x_test.to_dict(orient="records")
x_train

[{'pclass': '3rd', 'age': 45.0, 'sex': 'female'},

…
{‘pclass’: ‘3rd’, ‘age’: 31.19418104265403, ‘sex’: ‘male’},
{‘pclass’: ‘1st’, ‘age’: 36.0, ‘sex’: ‘male’},
…]

transfer = DictVectorizer()

x_train = transfer.fit_transform(x_train)
x_test = transfer.fit_transform(x_test)

x_train

<1050x6 sparse matrix of type '<class 'numpy.float64'>'
	with 3150 stored elements in Compressed Sparse Row format>

# 4.机器学习（模型训练）
estimator = RandomForestClassifier()

param_grid = {"n_estimators": [120,200,300,500,800,1200], "max_depth": [5, 8, 15, 25, 30]}
estimator = GridSearchCV(estimator, param_grid=param_grid, cv=5)

estimator.fit(x_train, y_train)

GridSearchCV(cv=5, error_score='raise',
       estimator=RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=1,
            oob_score=False, random_state=None, verbose=0,
            warm_start=False),
       fit_params=None, iid=True, n_jobs=1,
       param_grid={'n_estimators': [120, 200, 300, 500, 800, 1200], 'max_depth': [5, 8, 15, 25, 30]},
       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',
       scoring=None, verbose=0)

estimator.score(x_test, y_test)

0.7908745247148289

estimator.best_estimator_

RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=5, max_features='auto', max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=500, n_jobs=1,
            oob_score=False, random_state=None, verbose=0,
            warm_start=False)