def prep_store_data():
#get the data from acquire file
store = acquire.get_all_data()
#Add a 'month' and 'day of week' column
store["month"] = store.index.month_name()
store["weekday"] = store.index.day_name()
#Add sales total column from sale_amount and item_price
store["sales_total"] = store.sale_amount * store.item_price
#new column that is the result of the current sales - the previous days sales.
store["sales_diff(1)"] = store.sales_total.diff(1)
# Change dtypes of numeric columns to object and category
store = (store.astype({
'sale_id': object,
'store_id': object,
'store_zipcode': object,
'item_id': object,
'item_upc12': object,
'item_upc14': object,
'month': 'category',
'weekday': 'category'
}))
numeric_hists(store)
return store
def prepare_sale():
df = acquire.get_all_data(use_cache=True)
df['sale_date'] = pd.to_datetime(df['sale_date'])
df = df.sort_values(by='sale_date').set_index('sale_date')
df['month'] = df.index.strftime('%m-%b')
df['day_of_week'] = df.index.strftime('%w-%A')
df['total_sales'] = df['sale_amount'] * df['item_price']
sales_sum = df.resample("D")[['total_sales']].sum()
sales_sum['sales_differences'] = sales_sum['total_sales'].diff()
return df
def prep_sales_data():
df = acquire.get_all_data(use_cache=True)
df['sale_date'] = pd.to_datetime(df['sale_date'])
df.sale_amount.plot().set_title(
'The distribution of sale amount over time')
df.item_price.plot().set_title('The distribution of item price over time')
df = df.sort_values('sale_date').set_index('sale_date')
df["month"] = df.index.month_name()
df["day_of_week"] = df.index.day_name()
df['sales_total'] = df.sale_amount * df.item_price
return df
def prepare_store_data():
# convert date to date_time format
df = acquire.get_all_data()
df['sale_date'] = pd.to_datetime(df['sale_date'])
#sort df by `sale_date`
df.sort_values('sale_date', inplace = True)
#set the index to tbe the datetime variable
by_date = df.set_index('sale_date')
# create 'month' column
by_date['month'] = list(by_date.index.month)
# create 'nameofdayofweek' column
by_date['nameofdayofweek'] = list(by_date.index.weekday_name)
# create 'dayofweek'
by_date['dayofweek'] = list(by_date.index.dayofweek)
# create 'sales_total' column
by_date['sales_total'] = by_date['sale_amount']*by_date['item_price']
return by_date
import acquire
import pandas as pd
from datetime import timedelta, datetime
import numpy as np
df = acquire.get_all_data()
# format
fmt = '%a, %d %b %Y %H:%M:%S %Z'
df.sale_date = pd.to_datetime(df.sale_date, format=fmt)
df = df.sort_values(by='sale_date').set_index('sale_date')
df.sale_amount.plot()
df.item_price.plot()
df['month'] = df.index.strftime('%m-%b')
df['weekday'] = df.index.strftime('%w-%a')
df.head()
df[['month', 'weekday']].head()
(df.sale_amount.astype('int') == df.sale_amount).all()
df.sale_amount = df.sale_amount.astype('int')
df.item_price.plot.hist()
df['sales_total'] = df.sale_amount * df.item_price
df.drop(columns='sale_total')
df.head()