python pandas基础

读取文档

#导入csv函数 food_info=pandas.read_csv("food_info.csv") print(type(food_info)) print(food_info.dtypes)

基本操作

#帮助文档 print(help(pandas.read_csv)) food_info.head(3)#前三行数据 food_info.tail(5)#后5行数据 food_info.columns#列名 food_info.shape#大小 food_info.loc[0]#定位第一个数据 food_info.loc[3:6] food_info.loc[[2,5,10]]#第2，5,10行数据 # # #打印整列 ndb_col=food_info["NDB_No"] print(ndb_col) columns=["Zinc_(mg)","Copper_(mg)"] zinc_copper=food_info[columns] print(zinc_copper) # # col_names=food_info.columns.tolist()#以列表形式展示 gram_columns=[] for c in col_names: if c.endswith("(g)"): gram_columns.append(c) gram_df=food_info[gram_columns] print(gram_df.head(3)) # #新加入一列 water_enger=food_info["Water_(g)"]*food_info["Energ_Kcal"] iron_grams=food_info["Iron_(mg)"]/1000 food_info["Iron_(g)"]=iron_grams # #排序 food_info.sort_values("Sodium_(mg)",inplace=True) print(food_info["Sodium_(mg)"]) food_info.sort_values("Sodium_(mg)",inplace=True,ascending=False)#降序 #

观察属性

import pandas as pd import numpy as np titanic_survival=pd.read_csv("titanic_train.csv") titanic_survival.head #观察属性 age=titanic_survival["Age"] age_is_null=pd.isnull(age)#返回缺失值的索引 age_null_true=age[age_is_null]#找出所有的缺失值 age_null_count=len(age_null_true) #

清除缺失值

#需要清除缺失值 mean_age=sum(titanic_survival["Age"])/len(titanic_survival["Age"]) print(mean_age) #返回值是nan #正确做法 good_ages=titanic_survival["Age"][age_is_null==False] correct_mean_age=sum(good_ages)/len(good_ages) print(correct_mean_age) # #或者直接使用函数 correct_mean_age=titanic_survival["Age"].mean() print(correct_mean_age) #

求某个属性值的平均值、和

#求某一个属性值的平均值 passenger_classes=[1,2,3] fares_by_class={} for this_class in passenger_classes: pclass_rows=titanic_survival[titanic_survival["Pclass"]==this_class] pclass_fares=pclass_rows["Fare"] fare_for_class=pclass_fares.mean() fares_by_class[this_class]=fare_for_class print(fares_by_class) # #直接使用函数 port_stats=titanic_survival.pivot_table(index="Embarked",values=["Fare", "Survived"], aggfunc=np.sum) print(port_stats) passenger_age=titanic_survival.pivot_table(index="Embarked",values="Age") print(passenger_age)#默认值为求平均 #

去除缺失值

#去除缺失值 drop_na_columns=titanic_survival.dropna(axis=1) new_titanic_survival=titanic_survival.dropna(axis=0,subset=["Age","Sex"]) #

定位

#定位 row_index_83_age=titanic_survival.loc[83,"Age"] row_index_1000_pclass=titanic_survival.loc[766,"Pclass"] print(row_index_83_age) print(row_index_1000_pclass) #

排序

#排序 new_titanic_survival=titanic_survival.sort_values("Age",ascending=False)#样本编号乱序 titanic_reindex=new_titanic_survival.reset_index(drop=True)#样本编号也改为从0开始 #