1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
|
import pandas as pd
from bs4 import BeautifulSoup
import requests
# Table names:
# fact_sales_order
# fact_purchase_orders
# fact_payment
# dim_transaction
# dim_staff
# dim_payment_type
# dim_location
# dim_design
# dim_date
# dim_currency
# dim_counterparty
def create_fact_sales_order(dict_of_df):
df_sales = dict_of_df["sales_order"]
df_sales.index.name = "sales_record_id"
df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date
df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time
df_sales["last_updated_date"] = pd.to_datetime(
df_sales["last_updated"]).dt.date
df_sales["last_updated_time"] = pd.to_datetime(
df_sales["last_updated"]).dt.time
fact_sales_order = df_sales.loc[
:,
[
"sales_record_id",
"sales_order_id",
"created_date",
"created_time",
"last_updated_date",
"last_updated_time",
"sales_staff_id",
"counterparty_id",
"units_sold",
"unit_price",
"currency_id",
"design_id",
"agreed_payment_date",
"agreed_delivery_date",
"agreed_delivery_location_id",
],
]
return fact_sales_order
# fact_purchase_order from purchase_order
def create_fact_purchase_orders(dict_of_df):
df_po = dict_of_df["purchase_order"]
df_po.index.name = "purchase_record_id"
df_po["created_date"] = df_po["created_at"].date()
df_po["created_time"] = df_po["created_at"].dt.time
df_po["last_updated_date"] = df_po["last_updated_at"].date()
df_po["last_updated_time"] = df_po["last_updated_at"].dt.time
df_po["agreed_delivery_date"] = pd.to_datetime(
df_po["agreed_delivery_date"], format="%Y-%m-%d"
)
df_po["agreed_payment_date"] = pd.to_datetime(
df_po["agreed_payment_date"], format="%Y-%m-%d"
)
df_po.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True)
return df_po
def create_fact_payment(dict_of_df):
df_payment = dict_of_df["payment"]
df_payment.index.name = "payment_record_id"
df_payment["created_date"] = df_payment["created_at"].date()
df_payment["created_time"] = df_payment["created_at"].time
df_payment["last_updated_date"] = df_payment["last_updated"].date()
df_payment["last_updated_time"] = df_payment["last_updated"].time
df_payment["payment_date"] = pd.to_datetime(
df_payment["payment_date"], format="%Y-%m-%d")
fact_payment = df_payment.loc[
:,
[
"payment_record_id",
"payment_id",
"created_date",
"created_time",
"last_updated_date",
"last_updated_time",
"transaction_id",
"counterparty_id",
"payment_amount",
"currency_id",
"payment_type_id",
"paid",
"payment_date",
],
]
return fact_payment
# test passed
def create_dim_transaction(dict_of_df):
df_transaction = dict_of_df["transaction"].drop(
labels=["created_at", "last_updated"], axis=1
)
return df_transaction
# test passed
def create_dim_location(dict_of_df):
df_loc = (
dict_of_df["address"]
.drop(labels=["created_at", "last_updated"], axis=1)
.rename(columns={"address_id": "location_id"}))
return df_loc
def create_dim_counterparty(dict_of_df):
df_prefixed_address=dict_of_df["address"].add_prefix(
"counterparty_legal_", axis=1
)
df_cp=pd.merge(
dict_of_df["counterparty"],
df_prefixed_address,
left_on="legal_address_id",
right_on="counterparty_legal_address_id",
how="outer",
)
df_cp.drop(
columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True
)
return df_cp
# test passed
def create_dim_date(dict_of_df):
fact_dfs=[
create_fact_payment(dict_of_df),
create_fact_purchase_orders(dict_of_df),
create_fact_sales_order(dict_of_df),
]
date_col_names=[
col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name
]
list_of_date_columns=[]
for df in fact_dfs:
for col in date_col_names:
list_of_date_columns.append(df[col])
sr_date=pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]")
df_date=pd.DataFrame(data=sr_date, columns=["date_id"])
df_date.drop_duplicates(inplace=True)
df_date["year"]=df_date["date_id"].dt.year
df_date["month"]=df_date["date_id"].dt.month
df_date["day"]=df_date["date_id"].dt.day
df_date["day_of_week"]=df_date["date_id"].dt.dayofweek
df_date["day_name"]=df_date["date_id"].dt.day_name()
df_date["month_name"]=df_date["date_id"].dt.month_name()
df_date["quarter"]=df_date["date_id"].dt.quarter
return df_date
# tests passed
def scrape_currency_names():
response=requests.get("https://www.xe.com/currency/").content
soup=BeautifulSoup(response, "html.parser")
currency=[
item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"})
]
sr=pd.Series(currency)
df_cur=sr.str.split(pat=" - ", expand=True).rename(
{0: "currency_code", 1: "currency_name"}, axis=1
)
return df_cur
# tests passed
def create_dim_currency(dict_of_df, names=scrape_currency_names()):
df_cur=dict_of_df["currency"].drop(
labels=["created_at", "last_updated"], axis=1)
dim_cur=pd.merge(
df_cur, names, left_on="currency_code", right_on="currency_code", how="inner"
)
return dim_cur
# tests passed
def create_dim_payment_type(dict_of_df):
df_payment_type=dict_of_df["payment_type"]
dim_payment_type=df_payment_type.loc[:, [
"payment_type_id", "payment_type_name"]]
return dim_payment_type
# tests passed
def create_dim_design(dict_of_df):
df_design=dict_of_df["design"]
dim_design=df_design.loc[
:, ["design_id", "design_name", "file_name", "file_location"]
]
return dim_design
# tests passed
def create_dim_staff(dict_of_df):
staff_department=pd.merge(
dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left"
)
dim_staff=staff_department.loc[
:,
[
"staff_id",
"first_name",
"last_name",
"department_name",
"location",
"email_address",
],
]
return dim_staff
|
