python 泰坦尼克简单数据分析

import numpy as np
import pandas as pd
import random as rnd

import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.linear_model import LogisticRegression

df_train = pd.read_csv(‘titanic-train.csv’)
df_test = pd.read_csv(‘titanic-test.csv’)

df_train.head()
df_test.tail()
df_train.columns
df_test.columns
df_train.info()
df_test.info()
df_train.describe()

df_train[[‘Pclass’,‘Survived’]].groupby([‘Pclass’]).mean()
df_train[[‘Sex’,‘Survived’]].groupby([‘Sex’]).mean()

df_train[‘Age’].hist(bins=20)
g = sns.FacetGrid(df_train, col=‘Survived’)
g.map(plt.hist, ‘Age’, bins=20)
plt.show()

删除 ‘Name’, ‘Ticket’, ‘Fare’, ‘Cabin’, ‘Embarked’ 数据

train_df = df_train.drop([‘Name’, ‘Ticket’, ‘Fare’, ‘Cabin’, ‘Embarked’], axis = 1)
test_df = df_test.drop([