题目1.开始了解你的数据–探索Chipotle快餐数据
import pandas as pd
pd.set_option('display.max_columns',1000)
data = pd.read_csv(r'F:\Desktop\exercise_data\chipotle.tsv',sep='\t')
print(data.head(10))
print('数据集尺寸:',data.shape)
print('打印数据集列名:',data.columns)
print('打印数据集的索引:',data.index)
data_1 = data[['item_name','quantity']].groupby('item_name',as_index=False).agg('sum')
data_esc = data_1.sort_values(by='quantity',ascending=False)
print('被下单数最多商品(item)是:',data_esc.head(1))
data_unique = data['item_name'].nunique
print('在item_name这一列中,一共有多少种商品被下单',data_unique)
data_max = data['choice_description'].value_counts().head(1)
print(data_max)
dollarizer = lambda x: float(x[1:-1])
data['item_price'] = data['item_price'].apply(dollarizer)
print(data['item_price'])
print(data.info())
data['sub_total'] = round(data['quantity']*data['item_price'],2)
print('在该数据集对应的时期内,收入(revenue)是:',data['sub_total'].sum())
order_id_nunique = data['order_id'].nunique()
print('在该数据集对应的时期内,一共有订单:',order_id_nunique)
order_id_mean = data[['order_id','sub_total']].groupby('order_id',as_index=False).agg({'sub_total':'sum'})
print('每一单(order)对应的平均总价是:',order_id_mean['sub_total'].mean())
print('每一单(order)对应的平均总价是:',round(order_id_mean['sub_total'].mean(),2) )
print('一共有多少种不同的商品被售出:',data['item_name'].nunique())
题目2.数据过滤与排序–探索2012欧洲杯数据