python資料分析-資料處理

標籤：strftime   ccf   匹配   height   splay   14.   分享圖片   http   格式   

資料匯入：

 

 

 匯入csvfrom pandas import read_csv;df = read_csv(‘D://PA//4.1//1.csv‘)匯入文本，要轉成UTF-8無BOM格式：from pandas import read_table;df = read_table(‘D://PA//4.1//2.txt‘)匯入exclefrom pandas import read_excel;df = read_excel(‘C:/PA/4.1/3.xlsx‘)

View Code資料匯出：資料的匯出：

from pandas import DataFrame;df = DataFrame({    ‘age‘: [21, 22, 23],     ‘name‘: [‘KEN‘, ‘John‘, ‘JIMI‘]});df.to_csv("c:/PA/4.1/df.csv");#不匯入序號df.to_csv("c:/PA/4.1/df.csv", index=False);

View Code重複值處理：

from pandas import read_csv;df = read_csv(‘C:/PA/4.1/data.csv‘)newDF = df.drop_duplicates();

View Code缺失值處理：

from pandas import read_csv;df = read_csv(‘C:/PA/4.4/data.csv‘)newDF = df.dropna();

View Code空格值處理：

from pandas import read_csv;df = read_csv(‘C:/PA/4.5/data.csv‘)newDF = df["name"].str.strip();df["name"]=newDF;

View Code欄位抽取：

astype(str) 轉換成字元型資料，以便於處理。

from pandas import read_csv;df = read_csv(‘C:/PA/4.6/data.csv‘)df["tel"]=df["tel"].astype(str);bands=df["tel"].str.slice(0,3);areas=df["tel"].str.slice(3,7);numbs=df["tel"].str.slice(7,11);

View Code欄位拆分：

from pandas import read_csv;df=read_csv("C:/PA/4.7/data.csv");newDF=df["name"].str.split(" ",1,True);newDF.columns=["band","name"];

View Code記錄抽取：

import pandas;from pandas import read_csv;df=read_csv("C:/PA/4.8/data.csv",sep="|");df[df.comments>1000];df[df.comments.between(1000,10000)];df[pandas.isnull(df.title)];df[df.title.str.contains("台電",na=False)];df[(df.comments>=1000)&(df.comments<=10000)]

View Code隨機抽樣：

import numpy;from pandas import read_csv;df=read_csv("C:/PA/4.9/data.csv");r=numpy.random.randint(0,10,3);df.loc[r,:];

View Code記錄合并 ：

import pandas;from pandas import read_csv;df1=read_csv("C:/PA/4.10/data1.csv",sep="|");df2=read_csv("C:/PA/4.10/data2.csv",sep="|");df3=read_csv("C:/PA/4.10/data3.csv",sep="|");df=pandas.concat([df1,df2,df3])

View Code欄位合并：

from pandas import read_csv;df = read_csv(     "C:/PA/4.11/data.csv",    sep=" ",     names=[‘band‘, ‘area‘, ‘num‘]);df = df.astype(str);tel = df[‘band‘] + df[‘area‘] + df[‘num‘]    

View Code欄位匹配：

import pandas;from pandas import read_csv;item=read_csv(        "C:/PA/4.12/data1.csv",        sep="|",        names=["id","comments","title"]);prices=read_csv(         "C:/PA/4.12/data1.csv",         sep="|",         names=["id","oldprice","newprice"]        )itemprices=pandas.merge(        item,        prices,        left_on="id",        right_on="id" );

View Code簡單計算：

import pandas;from pandas import read_csv;df=read_csv("C:/PA/4.13/data.csv",sep="|");result=df.price*df.numdf["sum"]=result

View Code資料標準化：

import pandas;from pandas import read_csv;df=read_csv("C:/PA/4.14/data.csv");scale=(df.score-df.score.min())/(df.score.max()-df.score.min())

View Code資料分組：

import pandas;from pandas import read_csv;df = read_csv("C:\\PA\\4.15\\data.csv", sep=‘|‘);bins = [min(df.cost)-1, 20, 40, 60, 80, 100, max(df.cost)+1];labels = [‘20以下‘, ‘20到40‘, ‘40到60‘, ‘60到80‘, ‘80到100‘, ‘100以上‘];pandas.cut(df.cost, bins)pandas.cut(df.cost, bins, right=False)pandas.cut(df.cost, bins, right=False, labels=labels)

View Code日期轉換：

import pandas;from pandas import read_csv;from pandas import to_datetime;df = read_csv("C:\\PA\\4.16\\data.csv",encoding="utf-8");df_dt=to_datetime(df.註冊時間,format="%Y/%m/%d");

View Code日期格式化：

import pandas;from pandas import read_csv;from pandas import to_datetime;df = read_csv("C:\\PA\\4.16\\data.csv",encoding="utf-8");df_dt=to_datetime(df.註冊時間,format="%Y/%m/%d");df_dt_str=df_dt.apply(lambda x:datatime.strftime(x,"%d-%m-%Y"))

View Code日期抽取：

 

import pandas;from pandas import read_csv;from pandas import to_datetime;df = read_csv("C:\\PA\\4.18\\data.csv",encoding="utf-8");df_dt=to_datetime(df.註冊時間,format="%Y/%m/%d");df_dt.dt.year;df_dt.dt.second;df_dt.dt.minute;df_dt.dt.hour;df_dt.dt.day;df_dt.dt.month;df_dt.dt.weekday;

View Code

 

python資料分析-資料處理