pandas数据预处理与透视表

以下代码是基于python3.5.0编写的

import pandas as pd import numpy as np titanic_survival = pd.read_csv("titanic_train.csv") # ---------------------------统计age列有多少值为空------------------------- age = titanic_survival["Age"] age_is_null = pd.isnull(age) age_null_true = age[age_is_null] age_null_count = len(age_null_true) print(age_null_count) #-------------------------求均值方法一---------------------------------------- good_ages = titanic_survival["Age"][age_is_null == False] #把age列中不为空的值赋值给good_ages correct_mean_age = sum(good_ages) / len(good_ages) print(correct_mean_age) #-------------------------求均值方法二---------------------------------------- correct_mean_age = titanic_survival["Age"].mean() #mean函数会自动取出age列中为空的值，然后赋值给correct_mean_age print(correct_mean_age) #-----------------------------统计每种等级船舱平均票价------------------------------ passenger_classes = [1, 2, 3] fares_by_class = {} for this_class in passenger_classes: pclass_rows = titanic_survival[titanic_survival["Pclass"] == this_class] #找出Pclass为1的所有行 pclass_fares = pclass_rows["Fare"] #找出Pclass为1的Fare列 fare_for_class = pclass_fares.mean() fares_by_class[this_class] = fare_for_class print(fares_by_class) # -----------------pivot_table透视表函数，找出每种Pclass所对应Survived的平均值------------------------------------- passenger_survival = titanic_survival.pivot_table(index="Pclass", values="Survived", aggfunc=np.mean) print(passenger_survival) passenger_age = titanic_survival.pivot_table(index="Pclass", values="Age", aggfunc=np.mean) print(passenger_age) port_stats = titanic_survival.pivot_table(index="Embarked", values=["Fare","Survived"], aggfunc=np.sum) print(port_stats)