Python数据分析可视化--Titanic

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib.pylab import style
style.use('ggplot')
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC,LinearSVC
import warnings
warnings.filterwarnings("ignore")

df = pd.read_csv('train.csv',index_col=None)
test_df = pd.read_csv('test.csv')

np.any(pd.isnull(df)) 

True

np.any(df["Embarked"].isnull())

True

df.describe()

df[['Pclass','Survived']].groupby(by=["Pclass"]).mean().sort_values(by="Survived",ascending=False)

df['Sex'].value_counts()

male      577
female    314
Name: Sex, dtype: int64

df[['Sex','Survived']].groupby(by=["Sex"]).mean().sort_values(by="Survived",ascending=False)

df[['SibSp','Survived']].groupby(by=["SibSp"]).mean().sort_index(ascending=False)

df[['Parch','Survived']].groupby(by=["Parch"]).mean().sort_index(ascending=False)

g1 = sns.FacetGrid(df,col="Survived")
g1.map(plt.hist,"Age",bins=20)
plt.show()

g2 = sns.FacetGrid(df,col="Survived",row="Pclass")
g2.map(plt.hist,"Age")
plt.show()

g3 = sns.FacetGrid(df,row="Embarked",height=3,aspect=1.6)
g3.map(sns.pointplot,"Pclass",'Survived','Sex',palette="deep",hue_order=["female","male"])
g3.add_legend()
plt.show()

g4 = sns.FacetGrid(df,row="Embarked",col="Survived",height=3,aspect=1.6)
g4.map(sns.barplot,'Sex','Fare',palette="deep",hue_order=["female","male"])
g4.add_legend()
plt.show()

df = df.drop(["Ticket","Cabin"],axis=1)

df['Age'].fillna(method="pad",inplace=True)
df["Embarked"].fillna(method="pad",inplace=True)

df["Embarked"]

0      S
1      C
2      S
3      S
4      S
      ..
886    S
887    S
888    S
889    C
890    Q
Name: Embarked, Length: 891, dtype: object

"""性别转换"""
df["Sex"] = df["Sex"].map({"female":1,"male":0}).astype(int)
#df.loc[df['Sex'] == 'male', 'Sex'] = 1       # 用数值1来代替male，用0来代替female
#df.loc[df['Sex'] == 'female', 'Sex'] = 0
"""登船口转换"""
df["Embarked"] = df["Embarked"].map({"S":0,"C":1,"Q":2}).astype(int)