笔记Day02-1 Pandas

import pandas as pd
food_info=pd.read_csv("C:/Users/de/Desktop/唐宇迪数据集/food_info.csv")
print(type(food_info))#之前学习的numpy的类型是ndarray
print(food_info.dtypes)#pandas中常见的类型int float Object(在pandas中称字符型为object ) datatime bool 
print(help(pd.read_csv))

print(food_info.head())#显示前五条数据
print(food_info.head(3))#显示前三条数据

print(food_info.tail())#显示后几行数据

 

print(food_info.columns)#输出表头各个指标

print(food_info.shape)#输出一共多少个样本 每个样本有几个指标

print(food_info.loc[0])#获取第一行数据

print(print(food_info.loc[3:5]))

numbers=[2,5,10]
print(food_info.loc[numbers])

#取某一列
ndb_col=food_info["NDB_No"]
print(ndb_col)

或者 

colname=["NDB_No"]#或者colname="NDB_No"
print(food_info[colname])#如果获取两个列 就可以这么做 把列名放到list结构中 在传给dataframe

#数据中有的单位是g  有的是mg 进行查找
columns=food_info.columns.tolist()
print(columns)
gram_columns=[]
for c in columns:
    if c.endswith("(g)"):
        gram_columns.append(c)
print(food_info[gram_columns].head(3))

#将某一列的mg转换成g
col=food_info["Iron_(mg)"]/1000
print(food_info["Iron_(mg)"])
print('****')
print(col)

water_energy=food_info["Water_(g)"]*food_info["Energ_Kcal"]
iron_grams=food_info["Iron_(mg)"]/1000
print(food_info.shape)
food_info["new_col"]=iron_grams#进行新增一列
print(food_info.shape)

max_calories=food_info['Energ_Kcal'].max()
print(max_calories)#min max mean 求出某一列的最小值.....

print(food_info.shape)
#对数据进行排序 默认从小到大 缺省值在最后 ascending=Flase 是从大到小排序
food_info.sort_values("Sodium_(mg)",inplace=True)#inplace 设置是否新生成一列
print(food_info["Sodium_(mg)"])
print(food_info.shape)

 

titanic_survival=pd.read_csv("C:/Users/de/Desktop/唐宇迪数据集/泰坦尼克号数据.csv")
print(titanic_survival.head(3))
#Survived 数据分类  Pclass 船的等级  SibSp兄弟姐妹数量 Parch家人数量 Fare 船票价格 embarked登船
age=titanic_survival["Age"]
print(age.loc[0:10])

#对于缺失值进行处理
age=titanic_survival["Age"]
age_isnull=pd.isnull(age)
print(age_isnull)#这里TRUE或者false可以当成一个索引
age_null_true=titanic_survival[age_isnull]
print(age_null_true)
age_null_count=len(age_null_true)
print(age_null_count)

mean_age=sum(titanic_survival["Age"])/len(titanic_survival["Age"])
print(mean_age)  #此时还没对缺省值做处理 所以在求年龄平均值会出现这种状况

age=titanic_survival["Age"]
good_ages=titanic_survival["Age"][pd.isnull(age)==False]
correct_mean_age=sum(good_ages)/len(good_ages)
print(correct_mean_age)

#也可以通过直接调用pandas中的mean
correct_mean_age=titanic_survival["Age"].mean()
print(correct_mean_age)

 

#计算每个舱位的不同等级座位对应的平均价格
passenger_classes=[1,2,3]
fares_by_class={}
for this_class in passenger_classes:
    pclass_row=titanic_survival[titanic_survival["Pclass"]==this_class]
    pclass_fares=pclass_row["Fare"]
    fare_for_class=pclass_fares.mean()
    fares_by_class[this_class]=fare_for_class
print(fares_by_class)

#统计乘坐不同种类的舱的获救的概率 之前可能会考虑用循环 这里可以不用
import  numpy as np
passenger_survival=titanic_survival.pivot_table(index="Pclass",values="Survived",aggfunc=np.mean)
print(passenger_survival)

#计算船舱等级对应的平均年龄 aggfunc默认是求均值

passenger_age=titanic_survival.pivot_table(index="Pclass",values="Age")
print(passenger_age)

#统计Embarked与Fare和Survived之间的关系
port_stats=titanic_survival.pivot_table(index="Embarked",values=["Fare","Survived"],aggfunc=np.sum)
print(port_stats)

 

#丢弃某一行中age sex是缺省值的数据
print(titanic_survival.shape)
new_data=titanic_survival.dropna(axis=0,subset=["Age","Sex"])

print(new_data.shape)

#定位到某一个具体的数据
row_index_83_age=titanic_survival.loc[83,"Age"]
print(row_index_83_age)

new_titanic_survival=titanic_survival.sort_values("Age",ascending=False)
print(new_titanic_survival[0:10])
#此时索引是乱的
titanic_reindexed=new_titanic_survival.reset_index(drop=True)
print(titanic_reindexed)

#自定义函数 获取第一百行的值
def hundredth_row(column):
    hundredth_item=column.loc[99]
    return  hundredth_item
hundredth_row=titanic_survival.apply(hundredth_row)
print(hundredth_row)

def not_null_count(column):
    column_null=pd.isnull(column)
    null=titanic_survival[column_null]
    return len(null)
null_count=titanic_survival.apply(not_null_count)
print(null_count)

 

def which_class(row):
    pclass=row["Pclass"]
    if pd.isnull(pclass):
        return "Unknown"
    elif pclass==1:
        return  "First Class"
    elif pclass==2:
        return "Second Class"
    elif pclass==3:
        return "Third Class"
classes=titanic_survival.apply(which_class,axis=1)
print(classes)

def generate_age_label(row):
    age=row["Age"]
    if pd.isnull(age):
        return "Unknown"
    elif age<18:
        return "minor"
    else:
        return "adult"
age_labels=titanic_survival.apply(generate_age_label,axis=1)
print(age_labels)

#计算成年人获救的概率
titanic_survival["age_labels"]=age_labels
age_group_survival=titanic_survival.pivot_table(index="age_labels",values="Survived")
print(age_group_survival)

Series

DataFrame是相当于pandas读取进来的矩阵

dataFrame中的某一行或者某一列就称之为series

import pandas as pd
fandango=pd.read_csv('E:/唐宇迪数据集/fandango.csv')
series_film=fandango["FILM"]
print(type(series_film))
print(series_film[0:5])

film_names=series_film.values
print(type(film_names))

上图结果说明Dataframe 中是Series  Series中是ndarray

import pandas as pd
from pandas import  Series
fandango=pd.read_csv('E:/唐宇迪数据集/fandango.csv')
series_film=fandango["FILM"]
film_names=series_film.values
series_rt=fandango["RottenTomatoes"]
rt_scores=series_rt.values
series_custom=Series(rt_scores,index=film_names)#用电影名字当索引查找分数
print(series_custom[['Do You Believe? (2015)','Avengers: Age of Ultron (2015)']])

print(series_custom[5:10])

#排序
original_index=series_custom.index.tolist()
sorted_index=sorted(original_index)
print(sorted_index)
sorted_by_index=series_custom.reindex(sorted_index)
print(sorted_by_index)

print('**********')
print(series_custom.sort_index())
print("***********************************************")
print(series_custom.sort_values())

#两个进行相加

import  numpy as np
print(np.add(series_custom,series_custom))

series_greater_than_50=series_custom[series_custom>50]

rt_critics=Series(fandango['RottenTomatoes'].values,index=fandango['FILM'])
rt_users=Series(fandango['RottenTomatoes_User'].values,index=fandango['FILM'])
rt_min=(rt_critics+rt_users)/2
print(rt_min)

fandango_films=fandango.set_index('FILM',drop=False)
print(fandango_films)

print(fandango_films['Avengers: Age of Ultron (2015)':'Hot Tub Time Machine 2 (2015)'])

print(fandango_films.loc['Avengers: Age of Ultron (2015)':'Hot Tub Time Machine 2 (2015)'])

movies=['Avengers: Age of Ultron (2015)','Hot Tub Time Machine 2 (2015)']
print(fandango_films.loc[movies])
#相当于有了两个index 一个可以用String类型进行索引 一个可以使用原来的数值进行索引

fandango_films=fandango.set_index('FILM',drop=False)
types=fandango_films.dtypes
print(types)
float_columns=types[types.values=='float64'].index
float_df=fandango_films[float_columns]
rt_mt_user=float_df[['RT_user_norm','Metacritic_user_nom']]
print(rt_mt_user)
a=rt_mt_user.apply(lambda x:np.std(x),axis=1)
print(a)