select city from c
where companyId>AVG(companyId)
where companyId>AVG(companyId)
import pandas as pd import numpy as np titanic_survival = pd.read_csv("titanic_train.csv") titanic_survival.head() |
|
import pandas as pd train_data = pd.read_csv("train.csv") # 将标签转为0,1,2,3,4,... # 去掉重复的 species = train_data['species'].unique() print species # 转为0,1,2,3,4,... species = pd.Series(range(0, len(species)), index=list(species)) print species # 修改标签数据为:0,1,2,3,4,... def fix_spieces(line): line['species'] = species.loc[line['species']] return line train_data = train_data.apply(fix_spieces, axis=1) print train_data[0:4] # 返回numpy数据。 # 下标从0开始。 # 取样本数据,所有行:第二列到最后一列。 train_data.values[0::, 2::] # 取标签数据,所有行:第一列。 train_data.values[0::, 1]