对数据操作的总结

导包

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

# visualization
import seaborn as sns
import matplotlib.pyplot as plt

# machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier

 

读文件

filename = r'F:\数据集\titanic'
train_df = pd.read_csv(filename+'\\train.csv')
test_df  = pd.read_csv(filename+'\\test.csv')
combine = [train_df, test_df]

 

查看信息

df.columns.values  #获取列的标题

df.shape

df.info()

df.describe（）

# 默认是描述数字类型的属性，而include= “O“ 则是描述object类型的熟悉， include= ”all“则是对所有属性的描述。

df.describe(include = 'all')

df.describe(include=['O'])

df.sample(5) 

df.head()

df.tail()

# 查找指定行

df.loc[df['列名'] > 500]

# 把有缺失值的显示出来
sample_incomplete_rows = housing[housing.isnull().any(axis=1)].head()

 

查看不同种类的个数和占比

print(train['Sex'].value_counts())
print()
print(train['Sex'].value_counts(normalize=True)) 

得到结果：
male      577
female    314
Name: Sex, dtype: int64

male      0.647587
female    0.352413
Name: Sex, dtype: float64

透视表

columns = ['Sex', 'Pclass', 'Embarked', 'SibSp', 'Parch