ubuntu 14.04 anaconda安装

转载

mb5ff980f81f3d8 2017-11-01 15:34:00

文章标签 python linux 环境变量 .net bash 文章分类 代码人生

Python的准备工作

Python 一个备受欢迎的点是社区支持很多，有非常多优秀的库或者模块。但是某些库之间有时候也存在依赖，所以要安装这些库也是挺繁琐的过程。但总有人忍受不了这种繁琐，都会开发出不少自动化的工具来节省各位客官的时间。其中，Anaconda是一个非常好的安装工具。

１. Anaconda安装

这是一个非常齐全的python发行版本，最新的版本提供了多达195个流行的python包，包含了我们常用的numpy、scipy等等科学计算的包。有了它，妈妈再也不用担心我焦头烂额地安装一个又一个依赖包了。Anaconda在手，轻松我有！下载地址如下：http://www.continuum.io/downloads，现在的版本有python2.7版本和python3.5版本，下载好对应版本、对应系统的anaconda，它实际上是一个sh脚本文件，大约280M左右。我下载的是linux版的python 2.7版本。

下载成功后，在终端执行（2.7版本）：

# bash Anaconda2-2.4.1-Linux-x86_64.sh

在安装的过程中，会问你安装路径，直接回车默认就可以了

2. 将python添加到环境变量中

如果在安装Anaconda的过程中没有将安装路径添加到系统环境变量中，需要在安装后手工添加：

1、在终端输入$sudo gedit /etc/profile，打开profile文件。

2、在文件末尾添加一行：export PATH=/home/grant/anaconda2/bin:$PATH，其中，将“/home/grant/anaconda2/bin”替换为你实际的安装路径。保存。

3. 使环境变量生效

方法1：

让/etc/profile文件修改后立即生效 ,可以使用如下命令:

# . /etc/profile

注意: . 和 /etc/profile 有空格

方法2：

让/etc/profile文件修改后立即生效 ,可以使用如下命令:

# source /etc/profile

附：Linux中source命令的用法

source命令：

source命令也称为“点命令”，也就是一个点符号（.）。source命令通常用于重新执行刚修改的初始化文件，使之立即生效，而不必注销并重新登录。

用法：

source filename 或 . filename

4. scikit-learn 安装

在终端执行命令：conda install scikit-learn

一直 “Enter" 或　”yes" 即可完成安装。

真的很方便。

5. scikit-learn 测试

#!usr/bin/env python
#-*- coding: utf-8 -*-

import sys
import os
import time
from sklearn import metrics
import numpy as np
import cPickle as pickle

reload(sys)
sys.setdefaultencoding('utf8')

# Multinomial Naive Bayes Classifier
def naive_bayes_classifier(train_x, train_y):
    from sklearn.naive_bayes import MultinomialNB
    model = MultinomialNB(alpha=0.01)
    model.fit(train_x, train_y)
    return model


# KNN Classifier
def knn_classifier(train_x, train_y):
    from sklearn.neighbors import KNeighborsClassifier
    model = KNeighborsClassifier()
    model.fit(train_x, train_y)
    return model


# Logistic Regression Classifier
def logistic_regression_classifier(train_x, train_y):
    from sklearn.linear_model import LogisticRegression
    model = LogisticRegression(penalty='l2')
    model.fit(train_x, train_y)
    return model


# Random Forest Classifier
def random_forest_classifier(train_x, train_y):
    from sklearn.ensemble import RandomForestClassifier
    model = RandomForestClassifier(n_estimators=8)
    model.fit(train_x, train_y)
    return model


# Decision Tree Classifier
def decision_tree_classifier(train_x, train_y):
    from sklearn import tree
    model = tree.DecisionTreeClassifier()
    model.fit(train_x, train_y)
    return model


# GBDT(Gradient Boosting Decision Tree) Classifier
def gradient_boosting_classifier(train_x, train_y):
    from sklearn.ensemble import GradientBoostingClassifier
    model = GradientBoostingClassifier(n_estimators=200)
    model.fit(train_x, train_y)
    return model


# SVM Classifier
def svm_classifier(train_x, train_y):
    from sklearn.svm import SVC
    model = SVC(kernel='rbf', probability=True)
    model.fit(train_x, train_y)
    return model

# SVM Classifier using cross validation
def svm_cross_validation(train_x, train_y):
    from sklearn.grid_search import GridSearchCV
    from sklearn.svm import SVC
    model = SVC(kernel='rbf', probability=True)
    param_grid = {'C': [1e-3, 1e-2, 1e-1, 1, 10, 100, 1000], 'gamma': [0.001, 0.0001]}
    grid_search = GridSearchCV(model, param_grid, n_jobs = 1, verbose=1)
    grid_search.fit(train_x, train_y)
    best_parameters = grid_search.best_estimator_.get_params()
    for para, val in best_parameters.items():
        print para, val
    model = SVC(kernel='rbf', C=best_parameters['C'], gamma=best_parameters['gamma'], probability=True)
    model.fit(train_x, train_y)
    return model

def read_data(data_file):
    import gzip
    f = gzip.open(data_file, "rb")
    train, val, test = pickle.load(f)
    f.close()
    train_x = train[0]
    train_y = train[1]
    test_x = test[0]
    test_y = test[1]
    return train_x, train_y, test_x, test_y

if __name__ == '__main__':
    data_file = "mnist.pkl.gz"
    thresh = 0.5
    model_save_file = None
    model_save = {}

    test_classifiers = ['NB', 'KNN', 'LR', 'RF', 'DT', 'SVM', 'GBDT']
    classifiers = {'NB':naive_bayes_classifier, 
                  'KNN':knn_classifier,
                   'LR':logistic_regression_classifier,
                   'RF':random_forest_classifier,
                   'DT':decision_tree_classifier,
                  'SVM':svm_classifier,
                'SVMCV':svm_cross_validation,
                 'GBDT':gradient_boosting_classifier
    }

    print 'reading training and testing data...'
    train_x, train_y, test_x, test_y = read_data(data_file)
    num_train, num_feat = train_x.shape
    num_test, num_feat = test_x.shape
    is_binary_class = (len(np.unique(train_y)) == 2)
    print '******************** Data Info *********************'
    print '#training data: %d, #testing_data: %d, dimension: %d' % (num_train, num_test, num_feat)

    for classifier in test_classifiers:
        print '******************* %s ********************' % classifier
        start_time = time.time()
        model = classifiers[classifier](train_x, train_y)
        print 'training took %fs!' % (time.time() - start_time)
        predict = model.predict(test_x)
        if model_save_file != None:
            model_save[classifier] = model
        if is_binary_class:
            precision = metrics.precision_score(test_y, predict)
            recall = metrics.recall_score(test_y, predict)
            print 'precision: %.2f%%, recall: %.2f%%' % (100 * precision, 100 * recall)
        accuracy = metrics.accuracy_score(test_y, predict)
        print 'accuracy: %.2f%%' % (100 * accuracy) 

    if model_save_file != None:
        pickle.dump(model_save, open(model_save_file, 'wb'))