1
pip list
2
#或者
3
conda list
4
#其中，pip list 只能查看库，而 conda list 则可以查看库以及库的版本
5

6

7
pip install scipy
8
pip install scipy --upgrade
9
# 或者
10
conda install scipy
11
conda update scipy
12

13
# 更新所有库
14
conda update --all
15

16
# 更新 conda 自身
17
conda update conda
18

19
# 更新 anaconda 自身
20
conda update anaconda

1
#显示所有列
2
pd.set_option('display.max_columns', None)
3

4
#显示所有行
5
pd.set_option('display.max_rows', None)
6

7
#设置value的显示长度为100，默认为50
8
pd.set_option('max_colwidth',100)
9

10
#内嵌画图
11
%matplotlib inline
12

13
#单独画图
14
%matplotlib qt
15

16
#画图中文乱码、负号
17
plt.rcParams['font.sans-serif']=['Microsoft YaHei']
18
plt.rcParams['axes.unicode_minus']=False
19

20
#linux指定字体
21
from matplotlib.font_manager import FontProperties
22
zhfont = FontProperties(fname="/home/public/font/SimHei.ttf", size=14)
23
plt.xlabel('日期',fontproperties = zhfont,fontsize=14)
24
plt.xticks(fontproperties=zhfont)
25

26
#让一个cell同时有多个输出print
27
from IPython.core.interactiveshell import InteractiveShell
28
InteractiveShell.ast_node_interactivity = "all"

1
import numpy as np
2
import pandas as pd
3
import matplotlib.pyplot as plt
4
from matplotlib.figure import SubplotParams
5
#我们使用SubplotParams 调整了子图的竖直间距
6
#plt.figure(figsize=(12, 6), dpi=200, subplotpars=SubplotParams(hspace=0.3))
7

8
import scipy.stats as stats
9
import seaborn as sns
10
import statsmodels.api as sm

1
from sklearn import datasets    #本地数据
2
from sklearn.model_selection import train_test_split    #进行数据分割
3

4
from sklearn.feature_extraction import DictVectorizer  #特征抽取和向量化
5
from sklearn.preprocessing import PolynomialFeatures   #多项式特征构造
6

7
from sklearn.feature_selection import VarianceThreshold  #基于方差特征选择
8
from sklearn.feature_selection import SelectKBest,SelectPercentile  #特征选择
9
#For classification: chi2, f_classif, mutual_info_classif
10
#For regression: f_regression, mutual_info_regression
11
from sklearn.feature_selection import RFE   #递归特征消除 (Recursive Feature Elimination)
12
from sklearn.feature_selection import SelectFromModel   #基于模型选择特征
13

14
from sklearn.decomposition import PCA  #主成分分析
15
from sklearn.manifold import MDS  #多维尺度分析
16
from sklearn.manifold import TSNE  #T分布和随机近邻嵌入
17

18
from sklearn.pipeline import Pipeline       #管道
19
from sklearn import metrics      #模型评估
20
from sklearn.model_selection import GridSearchCV  #网格搜索交叉验证
21
from sklearn.model_selection import KFold  #K折交叉验证
22
from sklearn.model_selection import cross_val_score  #交叉验证
23

24
from sklearn.linear_model import LinearRegression  #线性回归
25

26
from sklearn.linear_model import LogisticRegression  #逻辑回归
27

28
from sklearn import svm    #支持向量机
29

30
from sklearn.tree import DecisionTreeClassifier  #决策树
31
from sklearn.ensemble import RandomForestClassifier  #随机森林
32
from sklearn.ensemble import GradientBoostingClassifier  #梯度提升树
33

34
from sklearn.naive_bayes import MultinomialNB  #多项式朴素贝叶斯
35
from sklearn.naive_bayes import BernoulliNB  #伯努利朴素贝叶斯
36
from sklearn.naive_bayes import GaussianNB  #高斯朴素贝叶斯
37

38
from sklearn.neighbors import KNeighborsClassifier  #k紧邻
39

40
from sklearn.cluster import KMeans   #k均值聚类
41
from sklearn.cluster import DBSCAN  #基于密度的空间聚类
42
from sklearn.cluster import SpectralClustering  #谱聚类
43
from sklearn.cluster import Birch  #层次聚类
44

45
from sklearn.externals import joblib  #保存模型

1
"""
2
===========================
3
@File  : ${NAME}
4
@Author: DataShare
5
@Date  : ${DATE} ${TIME}
6
===========================
7
"""