pandas数据分析泰坦尼克号船员信息

first_rows=food_info.head(3)#打印前3行
print(first_rows)
print(food_info.columns)#显示表头
print(food_info.shape)#总的数据规模

import pandas as pd
food_info=pd.read_csv("food_info.csv")
print(food_info)
#读取数据并显示，dataframe格式

#print(food_info.loc[6])#利用索引查找指定行
#print(food_info.loc[3:6])
print(food_info.loc[[2,5,10]])

#选取指定的列进行打印
zinc_copper = food_info[["Zinc_(mg)", "Copper_(mg)"]]
print(zinc_copper)

#打印以g单位的营养物质
col_names=food_info.columns.to_list()
print(col_names)
gram_colunms=[]
for c in col_names:
    if c.endswith("(g)"):
        gram_colunms.append(c)
print(gram_colunms)
gram_df=food_info[gram_colunms]
print(gram_df.head(3))

#进行加减乘除运算
print(food_info["Iron_(mg)"])
print(food_info["Iron_(mg)"]/1000)
print(food_info["Iron_(mg)"]*2)
water_energy=food_info["Water_(g)"]*food_info["Energ_Kcal"]
print(water_energy)

#把食物中铁的mg转换成g
iron_grams=food_info["Iron_(mg)"]/1000
food_info["Iron_(g)"]=iron_grams
print(food_info["Iron_(g)"])

#进行排序sort，空的NaN放最后
print(food_info["Sodium_(mg)"])
food_info.sort_values("Sodium_(mg)",inplace=True,ascending=False)
print(food_info["Sodium_(mg)"])

#泰坦尼克号船员分析
import pandas as pd
import numpy as np
titanic=pd.read_csv("titanic_train.csv")
titanic.head()

#对缺失的数据进行统计
age=titanic["Age"]
age_is_null=pd.isnull(age)
print(age_is_null)
age_null_true=age[age_is_null]
print(age_null_true)
age_null_count=len(age_null_true)
print(age_null_count)

#计算年龄的平均值
correct_mean_age=titanic["Age"].mean()
print(correct_mean_age)

#每个class的平均票价
passenger_classes = [1, 2, 3]
fares_by_class = {}
for this_class in passenger_classes:
    pclass_rows = titanic[titanic["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)

#买不同票的人生存几率
passenger_survival=titanic.pivot_table(index="Pclass",values="Survived",aggfunc=np.mean)
print(passenger_survival)
#买不同票的人的平均年龄
passenger_age=titanic.pivot_table(index="Pclass",values="Age",aggfunc=np.mean)
print(passenger_age)
#在不同口岸上船的总费用和生存人数
port_stats=titanic.pivot_table(index="Embarked",values=["Fare","Survived"],aggfunc=np.sum)
print(port_stats)

drop_na_columns=titanic.dropna(axis=1)
new_titanic=titanic.dropna(axis=0,subset=["Age","Sex"])#删除了这两个为空的量
print(new_titanic)

row83=titanic.loc[83,"Age"]
row1000=titanic.loc[766,"Pclass"]#指定选取
print(row1000)

#对年龄进行排序，并对索引重新调整
new_survived=titanic.sort_values("Age",ascending=False)
print(new_survived[0:10])
titanic_reindexed=new_survived.reset_index(drop=True)
print(titanic_reindexed)

#自定义函数，功能是找数据
def hundredth_row(column):
    hundredth_item=column.iloc[99]
    return hundredth_item
hundredth_row=titanic.apply(hundredth_row)
print(hundredth_row)

#功能是统计空的变量个数是多少
def not_null_count(column):
    column_null=pd.isnull(column)
    null=column[column_null]
    return len(null)
column_null_count=titanic.apply(not_null_count)
print(column_null_count)

#功能是将连续的年龄离散化，分类
def is_minor(row):
    if row["Age"] < 18:
        return True
    else:
        return False

minors = titanic.apply(is_minor, axis=1)
#print minors

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.apply(generate_age_label, axis=1)
print(age_labels)

#统计各个年龄段的存活率
titanic['age_labels'] = age_labels
age_group_survival = titanic.pivot_table(index="age_labels", values="Survived")
print (age_group_survival)