Python数据分析与机器学习-Pandas

import pandas as pd import numpy as np # 泰克尼克号获救信号 ''' 'PassengerId' 乘客id 'Survived' 标签值 'Pclass' 仓位等级 'Name' 姓名 'Sex' 性别 'Age' 年龄 'SibSp' 兄弟姐妹数量 'Parch' 老人孩子总数 'Ticket' 票号 'Fare' 票价 'Cabin' 座位 'Embarked' 登船地点 ''' # pd.set_option('display.height', 1000) # pd.set_option('display.max_rows', 500) # pd.set_option('display.max_columns', 500) pd.set_option('display.width', 1000) titanic_survival = pd.read_csv("titanic_train.csv") print(titanic_survival.columns) print(titanic_survival.head()) # The Pandas library uses NaN, which stands for "not a number", to indicate a missing value. # we can use the pandas.isnull() function which takes a pandas series and returns a series of True and False values # Age没有值的数量 age = titanic_survival["Age"] print(age) age_is_null = pd.isnull(age) # pd.isnull true:是缺失值 flase:不是缺失值 print(age_is_null) age_null_true = age[age_is_null] print(len(age_null_true)) # Age缺失的数量 177 mean_age = sum(titanic_survival["Age"]) / len(titanic_survival["Age"]) print(mean_age) # nan good_ages = titanic_survival["Age"][age_is_null == False] print(sum(good_ages) / len(good_ages)) # 29.6991176471 correct_mean_age = titanic_survival["Age"].mean() # mean,平均年龄,自动筛选出没有age的数据 print(correct_mean_age) # 29.69911764705882 # 每个仓位票价的均价 passenger_classes = [1, 2, 3] fares_by_class = {} for this_class in passenger_classes: pclass_rows = titanic_survival[titanic_survival["Pclass"] == this_class] fare_for_class = pclass_rows["Fare"].mean() fares_by_class[this_class] = fare_for_class print(fares_by_class) # pivot_table 数据统计 # index 按照那个分组 # values 是我们要应用计算的列 # aggfunc 指定我们要执行的计算 passenger_Fare = titanic_survival.pivot_table(index="Pclass", values="Fare", aggfunc=np.mean) print(passenger_Fare) passenger_Fare = titanic_survival.pivot_table(index="Pclass", values="Fare") # 默认求平均值 print(passenger_Fare) # 按照Embarked进行分组，求Fare,Survived的和 port_stats = titanic_survival.pivot_table(index="Embarked", values=["Fare", "Survived"], aggfunc=np.sum) print(port_stats) print(titanic_survival) # 指定axis= 1或axis='columns' 删除任何具有空值的列 print(titanic_survival.fillna(0)) # 缺失值都填充为0 print(titanic_survival.dropna(axis=1)) # 删除有空值的列 print(titanic_survival.dropna(axis=0)) # 删除有空值的行 print(titanic_survival.dropna(axis=0, subset=["Age", "Sex"])) # 删除"Age", "Sex"有空值的行 row_index_83_age = titanic_survival.loc[83, "Age"] # 行号、列名 row_index_1000_pclass = titanic_survival.loc[766, "Pclass"] print(titanic_survival.loc[83]) print(row_index_83_age) print(titanic_survival.loc[766]) print(row_index_1000_pclass) new_titanic_survival = titanic_survival.sort_values("Age", ascending=True) print(new_titanic_survival) print(new_titanic_survival.loc[:10]) itanic_reindexed = new_titanic_survival.reset_index(drop=True) # 重建索引,返回重建索引后的矩阵 print(itanic_reindexed.loc[:10]) # 返回一系列的第一百个项目 def hundredth_row(column): return column.loc[99] # apply运行自定义函数 hundredth_row = titanic_survival.apply(hundredth_row) print(hundredth_row) # 缺失值的数量 def not_null_count(column): column_null = pd.isnull(column) return len(titanic_survival[column_null]) print(pd.isnull(titanic_survival)) print(len(pd.isnull(titanic_survival))) # 891 column_null_count = titanic_survival.apply(not_null_count, axis=0) # axis=0 列,axis=1 行 print(column_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 is_minor(row): if row["Age"] > 18: return True else: return False ages = titanic_survival.apply(is_minor, axis=1) print(ages) 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) titanic_survival['age_labels'] = age_labels # 成年、未成年的获救率 age_group_survival = titanic_survival.pivot_table(index="age_labels", values="Survived") print(age_group_survival)