-
Notifications
You must be signed in to change notification settings - Fork 0
/
Acquire.py
185 lines (146 loc) · 9.14 KB
/
Acquire.py
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
# Data is aquired from the company SQL Database, login credentials are required
#################################### Function Imports ##############################################
# OS allows us to check if the data is already stored on our computer
import os
# Pandas reads the data into the variable
import pandas as pd
# Holds login credentials for SQL Database in a seperate file not added to GitHub
# env should only be stored locally on your computer
# Add to your .gitignore file to ensure credentials not compromised by uploading online
from env import host, username, password
#################################### SQL Connection Function ##############################################
# Function uses Login credentials to create a connection to the company SQL database
# NOTE: BE SURE NOT TO ADD YOUR CREDENTIALS TO GITHUB WHEN RECREATING THE PROJECT
def get_db_url(db_name):
'''
Connect to the SQL database with credentials stored in env file.
Function parameter is the name of the database to connect to.
Returns url.
'''
# Creates the url and the function returns this url
url = f'mysql+pymysql://{username}:{password}@{host}/{db_name}'
return (url)
#################################### Acquire Zillow Home Data ##############################################
# Function connects to the SQL database to store the data in a variable which can be used throughout the project
# Saves the data as a .csv file, returns as a pandas data frame
def get_home_data():
'''
Connect to SQL Database with url function called within this function.
Checks if database is already saved to computer in csv file.
If no file found, saves to a csv file and assigns database to df variable.
If file found, just assigns database to df variable.
Returns df variable holding the Home Value database.
Includes all 52 Columns.
'''
# data_name allows the function to work no matter what a user might have saved their file name as
# First, we check if the data is already stored in the computer
# First conditional runs if the data is not already stored in the computer
if os.path.isfile('zillow_home.csv') == False:
# Querry selects the whole predicstion_2017 table from the database
sql_querry = '''
SELECT *
FROM properties_2017 as prop
JOIN predictions_2017 as pred ON pred.id = prop.id
AND (pred.transactiondate LIKE '2017-05-%%'
OR pred.transactiondate LIKE '2017-06-%%')
WHERE prop.propertylandusetypeid IN (260, 261, 263, 264, 266, 279)
;
'''
# Connecting to the data base and using the query above to select the data
# the pandas read_sql function reads the query into a DataFrame
df = pd.read_sql(sql_querry, get_db_url('zillow'))
# If any duplicates found, this removes them
# df.columns.duplicated() returns a boolean array, True for a duplicate or False if it is unique up to that point
# Use ~ to flip the booleans and return the df as any columns that are not duplicated
# df.loc accesses a group of rows and columns by label(s) or a boolean array
df = df.loc[:,~df.columns.duplicated()]
# The pandas to_csv function writes the data frame to a csv file
# This allows data to be stored locally for quicker exploration and manipulation
df.to_csv('zillow_home.csv')
# This conditional runs if the data has already been saved as a csv (if the function has already been run on your computer)
else:
# Reads the csv saved from above, and assigns to the df variable
df = pd.read_csv('zillow_home.csv', index_col=0)
return df
#################################### Acquire Zillow MVP Home Data ##############################################
# Function connects to the SQL database to store the data in a variable which can be used throughout the project
# Saves the data as a .csv file, returns as a pandas data frame
def get_mvp_home_data():
'''
Connect to SQL Database with url function called within this function.
Checks if database is already saved to computer in csv file.
If no file found, saves to a csv file and assigns database to df variable.
If file found, just assigns database to df variable.
Returns df variable holding the Home Value database for the MVP.
ID, bedroom/bathroom count, and taxvaluedollarcnt
'''
# data_name allows the function to work no matter what a user might have saved their file name as
# First, we check if the data is already stored in the computer
# First conditional runs if the data is not already stored in the computer
if os.path.isfile('zillow_home_mvp.csv') == False:
# Querry selects the whole dataframe, joining each table on their foreign keys
# Only selecting properties with transaction dates in May and June
sql_querry = '''
SELECT prop.id, calculatedfinishedsquarefeet, bedroomcnt, bathroomcnt, taxvaluedollarcnt
FROM properties_2017 as prop
JOIN propertylandusetype as land ON prop.propertylandusetypeid = land.propertylandusetypeid
JOIN predictions_2017 as pred ON pred.id = prop.id
AND (pred.transactiondate LIKE '2017-05-%%'
OR pred.transactiondate LIKE '2017-06-%%')
WHERE prop.propertylandusetypeid IN (260, 261, 263, 264, 266, 279);
'''
# Connecting to the data base and using the query above to select the data
# the pandas read_sql function reads the query into a DataFrame
df = pd.read_sql(sql_querry, get_db_url('zillow'))
# Removes duplicates if any
# df.columns.duplicated() returns a boolean array, True for a duplicate or False if it is unique up to that point
# Use ~ to flip the booleans and return the df as any columns that are not duplicated
# df.loc accesses a group of rows and columns by label(s) or a boolean array
df = df.loc[:,~df.columns.duplicated()]
# The pandas to_csv function writes the data frame to a csv file
# This allows data to be stored locally for quicker exploration and manipulation
df.to_csv('zillow_home_mvp.csv')
# This conditional runs if the data has already been saved as a csv (if the function has already been run on your computer)
else:
# Reads the csv saved from above, and assigns to the df variable
df = pd.read_csv('zillow_home_mvp.csv', index_col=0)
return df
########################################### Get Location Home Data ####################################################
def get_home_location():
'''
Connect to SQL Database with url function called within this function.
Checks if database is already saved to computer in csv file.
If no file found, saves to a csv file and assigns database to df variable.
If file found, just assigns database to df variable.
Returns df variable holding the Home Value database.
'''
# data_name allows the function to work no matter what a user might have saved their file name as
# First, we check if the data is already stored in the computer
# First conditional runs if the data is not already stored in the computer
if os.path.isfile('zillow_location.csv') == False:
# Querry selects neccessary columns to determine location of home and the tax values
#
sql_querry = '''
SELECT prop.id as property_id, prop.fips as county_id, prop.latitude, prop.longitude, prop.taxamount, prop.taxvaluedollarcnt
FROM properties_2017 as prop
JOIN predictions_2017 as pred ON pred.id = prop.id
AND (pred.transactiondate LIKE '2017-05-%%'
OR pred.transactiondate LIKE '2017-06-%%')
WHERE prop.propertylandusetypeid IN (260, 261, 263, 264, 266, 279);
'''
# Connecting to the data base and using the querry above to select the data
# the pandas read_sql function reads the query into a DataFrame
df = pd.read_sql(sql_querry, get_db_url('zillow'))
# Removes duplicates if any
# df.columns.duplicated() returns a boolean array, True for a duplicate or False if it is unique up to that point
# Use ~ to flip the booleans and return the df as any columns that are not duplicated
# df.loc accesses a group of rows and columns by label(s) or a boolean array
df = df.loc[:,~df.columns.duplicated()]
# The pandas to_csv function writes the data frame to a csv file
# This allows data to be stored locally for quicker exploration and manipulation
df.to_csv('zillow_location.csv')
# This conditional runs if the data has already been saved as a csv (if the function has already been run on your computer)
else:
# Reads the csv saved from above, and assigns to the df variable
df = pd.read_csv('zillow_location.csv', index_col=0)
return df