data_preprocessing.py · chenshiyang/Machine-Learning-with-Python

代码拉取完成,页面将自动刷新

扫描微信二维码支付

取消

支付完成

richgiteeai

Watch

不关注关注所有动态仅关注版本发行动态关注但不提醒动态

1 Star 0 Fork 2

chenshiyang/Machine-Learning-with-Python

forked from hzcc/Machine-Learning-with-Python

代码 Issues 0 Pull Requests 0 Wiki 统计流水线

服务

加入 Gitee

与超过 1400万开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)

免费加入

已有帐号? 立即登录

文件

master

分支 (1)

管理

master

该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。

项目仓库所选许可证以仓库主分支所使用许可证为准

克隆/下载

HTTPS SSH SVN SVN+SSH 下载ZIP

提示

下载代码请复制以下命令到终端执行

为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName 
git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥中

在 Gitee 上使用 SVN,请访问使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议配置并使用私人令牌替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

分支 1

标签 0

Machine-Learning-with-Python

data_preprocessing.py

data_preprocessing.py 1.13 KB

# Import the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Import the dataset 
dataset = pd.read_csv('data.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values

# Taking care of missing data
from sklearn.preprocessing import Imputer
imputer=Imputer(missing_values='NaN', strategy='mean', axis=0)
imputer=imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:,0] = labelencoder_X.fit_transform(X[:,0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)

# Splitting the dataset into the training set and test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=42)

# Feature scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)

一键复制编辑原始数据按行查看历史

Susan Li 提交于 2017年05月26日 17:00 +08:00 . Add file

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35

# Import the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Import the dataset 
dataset = pd.read_csv('data.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values

# Taking care of missing data
from sklearn.preprocessing import Imputer
imputer=Imputer(missing_values='NaN', strategy='mean', axis=0)
imputer=imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:,0] = labelencoder_X.fit_transform(X[:,0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)

# Splitting the dataset into the training set and test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=42)

# Feature scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)