전처리

import pandas as pd

 

file_path = 'chipotle.tsv'

chipo = pd.read_csv('chipotle.tsv', sep = '\t')

 

chipo.head()

chipo.shape

print(chipo.info())

chipo.describe()

chipo.columns

chipo.index

 

chipo['order_id'] = chipo['order_id'].astype(str)

chipo.describe()

 

item_count = chipo['item_name'].value_counts()[:10] # 상위 10개

item_count

 

for index. (val, cnt) in enumerate(item_count.iteritems(), 1):

print("Top", idex, ":", val, cnt)

 

order_count = chipo.groupby('item_name')['order_id'].count()

order_count[:10]

 

order_count = chipo.groupby('item_name')['quantity'].sum()

order_count[:10]

 

import numpy as np

import matplotlib.pyplot as plt

 

item_name_list = item_quantity.index.tolist()

x_pos = np.arange(len(item_name_list))

order_cnt = item_quantity.values.tolist()

 

plt.bar(x_pos, order_cnt, align='center')

plt.ylabel('ordered_item_count'_

plt.title('Distribution of all ordered item')

plt.show()

 

* item_quantity.index.tolist()

* item_quantity.values.tolist()

 

# 전처리, 문자를 숫자로, $ 제거

chipo['item_price']=chipo['item_price'].apply(lambada x: float(x[1:]))

 

# 주문당 평균 계산 금액

chipo.groupby('order_id')[item_price'].sum().mean()

 

# 한 주문 10달러 이상 지불한 주문 번호

chipo_orderid_group = chipo.groupby('order_id').sum()

 

results = chipo_orderid_group[chipo_orderid_group.item_price >=10]

print(results[:10])

print(results.index.values)

 

chipo_one_item = chipo[chipo.quantity == 1]

price_per_item = chipo_one_item.groupby('item_name').min()

price_per_item.sort_values(by = 'tem_price', ascending = False)[:10]

 

import pandas as pd

import numpy as np

import matplotlib.pyplot

 

file_path = 'drinks.csv'

drinks = pd.read_csv(file_path)

 

# 결측 데이터 전처리

 

print(drinks.isnull().sum())

print(drinks.dtypes)

drinks['continent'] = drinks['continent'].fillna('OT') # 결측값을 OT로 채울 것.

 

print(drinks.isnull().sum())

len(drinks['continent'.isnull())

 

# 파이차트 시각화

drinks['continent'].value_counts()