def using_item_id():
df = dr.get_data('train.xls')
item_id = dr.get_unqiue_list(list(df['Item_Id']))
item_id_list = list(dr.get_req_att(df, 'Item_Id'))
item_weight = list(dr.get_req_att(df, 'Item_Weight'))
item_fat_content = list(dr.get_req_att(df, 'Item_Fat_Content'))
item_type = list(dr.get_req_att(df, 'Item_Type'))
for outer_itr in item_id:
for itr in range(len(item_id_list)):
if item_id_list[itr] == outer_itr:
print(item_id_list[itr], item_weight[itr], item_fat_content[itr], item_type[itr])
input()
import dretrive as dr
df = dr.get_data('train.xls')
df = dr.get_req_att(df, ['Item_Type', 'Item_Fat_Content'])
item_list = dr.get_unqiue_list(df['Item_Type'])
print(item_list)
print("Length : ",len(item_list))
item_fat_list = dr.get_unqiue_list(df['Item_Fat_Content'])
print(item_fat_list)
print("Fat types : ", len(item_fat_list))
iweight = list(df['Item_Weight'])
ifat = list(df['Item_Fat_Content'])
itype = list(df['Item_Type'])
shopid = list(df['Outlet_Id'])
sales = list(df['Item_Outlet_Sales'])
mrp = list(df['Item_MRP'])
print('sales error count : ', dr.count_nan(sales))
'''
count_out019 = 0
for itr in range(len(iweight)):
#' ' '
#if (ifat[itr] == 'Low Fat' or ifat[itr] == 'LF' or ifat[itr] == 'low fat') and itype[itr] == 'Baking Goods' and shopid[itr] == 'OUT027' :
# print(iweight[itr], " ", sales[itr], " ", mrp[itr])
#' ' '
if shopid[itr] == 'OUT019':
count_out019 += 1
'''
#print(count_out019)
for outer_itr in list(dr.get_unqiue_list(shopid)):
count = 0
for itr in range(len(itype)):
if shopid[itr] == outer_itr :
if pd.isna(iweight[itr]):
count += 1
print(outer_itr, ': Check nan :', count)
df = dr.get_data('train.xls')
lis = ['Outlet_Id', 'Item_Outlet_Sales']
df = dr.get_req_att(df, lis)
# no empty values
'''
lis = df['Item_Outlet_Sales']
count = 0
for itr in lis:
if pd.isna(itr):
count += 1
print(count)
'''
#no cleaning required
shop_list = df['Outlet_Id']
std_shop_list = dr.get_unqiue_list(shop_list)
sale_list = df['Item_Outlet_Sales']
sales = []
for shop in std_shop_list:
count = 0
for itr in range(len(shop_list)):
if shop == shop_list[itr]:
count += sale_list[itr]
sales.append(count)
dv.bargraph(std_shop_list, sales)
import dretrive as dr
import pandas as pd
def generate_excel(df):
writer = pd.ExcelWriter('text.xls')
df.to_excel(writer, 'Sheet1', index=False)
writer.save()
if __name__ == '__main__':
df = dr.get_data('ctrain.xls')
std_shop_list = dr.get_unqiue_list(list(df['Outlet_Id']))
shop_list = list(df['Outlet_Id'])
item_visible = list(df['Item_Visibility'])
outlet_size = list(df['Outlet_Size'])
item_weight = list(df['Item_Weight'])
loc_type = list(df['Outlet_Loc_Type'])
outing = list(df['Outlet_Type'])
tot_visi_list = []
type_list = []
count_list = []
weight_list = []
final_list = []
loc_list = []
out_type = []
for itr in std_shop_list:
tot = 0
count = 0
weight = 0
for itr in range(len(item_fat_content)):
if item_fat_content[itr] == "Low Fat" or item_fat_content[
itr] == "low fat" or item_fat_content[itr] == "LF":
df.loc[itr, 'Item_Fat_Content'] = "Low Fat"
else:
df.loc[itr, 'Item_Fat_Content'] = "Regular"
return df
#stub
if __name__ == '__main__':
df = dr.get_data('train.xls')
item_id = dr.get_unqiue_list(list(df['Item_Id']))
item_id_list = list(dr.get_req_att(df, 'Item_Id'))
item_weight = list(dr.get_req_att(df, 'Item_Weight'))
print(dr.count_nan(item_weight))
item_fat_content = list(dr.get_req_att(df, 'Item_Fat_Content'))
item_type = list(dr.get_req_att(df, 'Item_Type'))
for outer_itr in item_id:
temp_list = []
for itr in range(len(item_id_list)):
if item_id_list[itr] == outer_itr:
#print(item_id_list[itr], item_weight[itr], item_fat_content[itr], item_type[itr])
temp_list.append(itr)
df = clean_nan(outer_itr, temp_list, item_weight, df)
item_weight = list(df['Item_Weight'])
print(dr.count_nan(item_weight))