pandas 常用方法

1.布尔筛选data.loc[（data['a'] ==a1）＆（data ['B'] ==b1），['A','B']]
2.data.apply ( func, axis=0) 
#axis=0 defines that function is to be applied on each column
3.#对于类别变量 填补缺失值
from scipy.stats import modemode(data['Gender'])
data['Gender'].fillna(mode(data['Gender']).mode[0], inplace=True)4.#利用多元变量组合  对 其他变量分类 创建透视表
impute_grps = data.pivot_table(values=["LoanAmount"], index=["Gender","Married","Self_Employed"], aggfunc=np.mean)5.利用上面的分类情况 填补缺失值
#iterate only through rows with missing LoanAmountfor i,row in data.loc[data['LoanAmount'].isnull(),:].iterrows():  ind = tuple([row['Gender'],row['Married'],row['Self_Employed']])#得到缺失值所对应的三元组  data.loc[i,'LoanAmount'] = impute_grps.loc[ind].values[0]#查询 多维索引6.#crosstab 用于可视化 一个取值做行标签一个做列标签 查看相关关系
pd.crosstab(data["Credit_History"],data["Loan_Status"],margins=True)7.#merge合并8.#排序
data_sorted = data.sort_values(['ApplicantIncome','CoapplicantIncome'], ascending=False)9.#plotting(Boxlplot Histogram)   比较分布 ApplicantIncome（通过 Loan_Status分类）查看不同取值对分布有无影响
%matplotlib inlinedata.boxplot(column="ApplicantIncome",by="Loan_Status")
data.hist(column="ApplicantIncome",by="Loan_Status",bins=30)10 分组pd.cut() ：传入三个切分点四个标签分为四组 用于变量分组离散化
def binning(col, cut_points, labels=None):  minval = col.min()  maxval = col.max()  break_points = [minval] + cut_points + [maxval]#连接列表 五个值  if not labels:    labels = range(len(cut_points)+1)  colBin = pd.cut(col,bins=break_points,labels=labels,include_lowest=True)  return colBin#Binning age:cut_points = [90,140,190]labels = ["low","medium","high","very high"]data["LoanAmount_Bin"] = binning(data["LoanAmount"], cut_points, labels)#创建新特征print pd.value_counts(data["LoanAmount_Bin"], sort=False)11.编码标称数据  Low/low...对于输入有误意思一样的数据统一标示，细粒度区分合并  或者是变成数值型便于模型利用
#Define a generic function using Pandas replace functiondef coding(col, codeDict):  colCoded = pd.Series(col, copy=True)  for key, value in codeDict.items():    colCoded.replace(key, value, inplace=True)  return colCoded #Coding LoanStatus as Y=1, N=0:print 'Before Coding:'print pd.value_counts(data["Loan_Status"])data["Loan_Status_Coded"] = coding(data["Loan_Status"], {'N':0,'Y':1})print '\nAfter Coding:'print pd.value_counts(data["Loan_Status_Coded"])
12.#防止变量类型不正确引起的麻
具有数字类别的类别变量被视为数字。
在其中一行中输入的字符（由于数据错误）的数字变量被认为是分类的
创建一个带有列名和类型的csv文件，用通用函数来读取文件并分配列数据类型
加载该文件后，我们可以遍历每一行，并使用列“type”将数据类型分配给“feature”列中定义的变量名。for i, row in colTypes.iterrows():  #i: dataframe index; row: each row in series format    if row['type']=="categorical":        data[row['feature']]=data[row['feature']].astype(np.object)    elif row['type']=="continuous":        data[row['feature']]=data[row['feature']].astype(np.float)print data.dtypes