Skip to content

Commit

Permalink
done merging the datasets!!!!
Browse files Browse the repository at this point in the history
  • Loading branch information
liangt2001 committed Oct 18, 2020
1 parent 0c7b991 commit 5d9d502
Show file tree
Hide file tree
Showing 3 changed files with 64 additions and 18 deletions.
2 changes: 1 addition & 1 deletion .vscode/settings.json
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
{
"python.pythonPath": "C:\\Users\\zam19\\AppData\\Local\\Programs\\Python\\Python38\\python.exe"
"python.pythonPath": "C:\\Users\\Tingyu\\AppData\\Local\\Programs\\Python\\Python39\\python.exe"
}
28 changes: 11 additions & 17 deletions main.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,30 +15,24 @@
# cities = pd.read_csv('cities.csv').set_index('City')
# CoL = pd.read_csv('movehubcostofliving.csv').set_index('City')
# QoL = pd.read_csv('movehubqualityoflife.csv').set_index('City')
prices = pd.read_csv('prices.csv').set_index('City')
prices = pd.read_csv('prices.csv')
tempCSV = pd.read_csv('tempByState.csv')
statesCSV = pd.read_csv('states.csv')
citiesCSV = pd.read_csv('uscities.csv')
rateCSV = pd.read_csv('unemployment_rate.csv')

citiesCSV = citiesCSV[['city', 'city_ascii', 'state_id', 'state_name', 'lat', 'lng', 'density']]
citiesCSV = citiesCSV.set_index('city')
citiesCSV = citiesCSV.join(tempCSV.set_index('Location'), on='state_name')
citiesCSV['location'] = citiesCSV['city'] + citiesCSV['county_name']
prices['location'] = prices['City'] + prices['County']

result = citiesCSV.join(prices.set_index('location'), on='location')
result = result.dropna().set_index('city')
result = result[['state_id', 'state_name', 'county_name', 'lat', 'lng', 'population', 'density', 'Value', 'Average Rental Cost']]

statesCSV = statesCSV.set_index('State')
tempCSV = tempCSV.set_index('Location')
tempCSV = tempCSV.join(statesCSV)
tempCSV = tempCSV[['Value', 'Code']]
tempCSV['State'] = tempCSV['Code']

# result = cities.join(QoL).join(CoL)
result = prices.join(tempCSV.set_index('State'), on='State')
result = result.join(rateCSV.set_index('State'), on='state_name')
result['Temp'] = result['Value']
result = result.dropna().drop(columns=['Code', 'Value'])
st.write(result)
st.write(citiesCSV)


result = citiesCSV.join(result, on=['city_ascii'])
result['Unemployment Rate'] = result['Rate']
result = result.drop(columns=['Rank', 'Value', 'Rate'])

st.write(result)

Expand Down
52 changes: 52 additions & 0 deletions unemployment_rate.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
State,Rate,Rank
Nebraska,4,1
Utah,4.1,2
Idaho,4.2,3
South Dakota,4.8,4
Vermont,4.8,4
North Dakota,5,6
Alabama,5.6,7
Georgia,5.6,7
Montana,5.6,7
Oklahoma,5.7,10
Arizona,5.9,11
Iowa,6,12
Virginia,6.1,13
Wisconsin,6.2,14
South Carolina,6.3,15
Indiana,6.4,16
New Hampshire,6.5,17
North Carolina,6.5,17
Wyoming,6.6,19
Colorado,6.7,20
Texas,6.8,21
Kansas,6.9,22
Maine,6.9,22
Maryland,6.9,22
Missouri,7,25
Alaska,7.4,26
Arkansas,7.4,26
Florida,7.4,26
Minnesota,7.4,26
Kentucky,7.6,30
Louisiana,7.6,30
Oregon,7.7,32
Mississippi,7.9,33
Connecticut,8.1,34
District of Columbia,8.5,35
Tennessee,8.5,35
Washington,8.5,35
Michigan,8.7,38
Delaware,8.9,39
Ohio,8.9,39
West Virginia,8.9,39
Pennsylvania,10.3,42
New Jersey,10.9,43
Illinois,11,44
Massachusetts,11.3,45
New Mexico,11.3,45
California,11.4,47
Hawaii,12.5,48
New York,12.5,48
Rhode Island,12.8,50
Nevada,13.2,51

0 comments on commit 5d9d502

Please sign in to comment.