求均值，表格中含有空值：

#The result of this is that mean_age would be nan. This is because any calculations we do with a null value also result in a null value
mean_age = sum(titanic_survival["Age"]) / len(titanic_survival["Age"])
print (mean_age)

运行结果：

正确的均值

age = titanic_survival["Age"]
# print(age.loc[0:10])
age_is_null = pd.isnull(age)
#we have to filter out the missing values before we calculate the mean.
good_ages = titanic_survival["Age"][age_is_null == False]
#print good_ages
correct_mean_age = sum(good_ages) / len(good_ages)
print (correct_mean_age)

运行结果：

mean()

# missing data is so common that many pandas methods automatically filter for it
correct_mean_age = titanic_survival["Age"].mean()
print (correct_mean_age)

运行结果：

计算不同类别的均值

#mean fare for each class
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

运行结果：

数据透视表 获救的比例

#index tells the method which column to group by
#values is the column that we want to apply the calculation to
#aggfunc specifies the calculation we want to perform
passenger_survival = titanic_survival.pivot_table(index="Pclass", values="Survived", aggfunc=np.mean)
print (passenger_survival)

运行结果：

平均年龄

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

运行结果：

一个量和两个量之间的关系

port_stats = titanic_survival.pivot_table(index="Embarked", values=["Fare","Survived"], aggfunc=np.sum)
print(port_stats)

运行结果：

dropna

#specifying axis=1 or axis='columns' will drop any columns that have null values
drop_na_columns = titanic_survival.dropna(axis=1)
new_titanic_survival = titanic_survival.dropna(axis=0,subset=["Age", "Sex"])
#print new_titanic_survival

loc函数

row_index_83_age = titanic_survival.loc[83,"Age"]
row_index_766_pclass = titanic_survival.loc[766,"Pclass"]
print (row_index_83_age)
print (row_index_766_pclass) 

运行结果：