In [1]:

    

import pandas as pd
from matplotlib import pyplot as plt

%matplotlib inline


    

In [101]:

    

empl_data = pd.read_csv('fixtures/training_data.csv')


    

In [102]:

    

print empl_data.shape


    

    




(108, 48)

In [103]:

    

empl_data.head()


    

    
Out[103]:






  

    

      

      
job_growth
      
job_growth_per
      
job_growth_min_1
      
job_growth_min_3
      
job_growth_min_6
      
job_growth_min_12
      
bls_avg_weeks_unemp_per
      
avg_weeks_unemp
      
avg_weeks_unemp_min_1
      
avg_weeks_unemp_min_3
      
...
      
taxes_min_1
      
taxes_min_3
      
taxes_min_6
      
taxes_min_12
      
outlays
      
spending
      
spending_min_1
      
spending_min_3
      
spending_min_6
      
spending_min_12
    
  
  

    

      
0
      
 0.085638
      
 0.000856
      
-0.075590
      
 0.175644
      
 0.274477
      
 0.050552
      
 19.5
      
-6.8
      
-6.890756
      
-6.790756
      
...
      
 19419
      
-59434
      
-61915
      
-104321
      
 194111
      
-64514
      
-40315
      
-65111
      
-55050
      
-69916
    
    

      
1
      
 0.099825
      
 0.000998
      
 0.085638
      
 0.357112
      
 0.012181
      
-0.064240
      
 19.1
      
-7.2
      
-6.790756
      
-6.590756
      
...
      
  5887
      
-61783
      
-58601
      
 -63905
      
 214660
      
-43965
      
-64514
      
-66908
      
-79764
      
-53288
    
    

      
2
      
 0.191616
      
 0.001916
      
 0.099825
      
-0.075590
      
-0.061617
      
 0.163955
      
 19.5
      
-6.8
      
-7.190756
      
-6.890756
      
...
      
-95459
      
 19419
      
 11021
      
  23761
      
 220483
      
-38142
      
-43965
      
-40315
      
-75885
      
-56112
    
    

      
3
      
 0.426579
      
 0.004266
      
 0.191616
      
 0.085638
      
 0.175644
      
 0.124027
      
 19.6
      
-6.7
      
-6.790756
      
-6.790756
      
...
      
-47571
      
  5887
      
-59434
      
 -80880
      
 219690
      
-38935
      
-38142
      
-64514
      
-65111
      
-80712
    
    

      
4
      
 0.251320
      
 0.002513
      
 0.426579
      
 0.099825
      
 0.357112
      
 0.231902
      
 18.6
      
-7.7
      
-6.690756
      
-7.190756
      
...
      
 81284
      
-95459
      
-61783
      
  18052
      
 188920
      
-69705
      
-38935
      
-43965
      
-66908
      
-63367
    
  

5 rows × 48 columns

In [107]:

    

fig, axs = plt.subplots(1, 3, sharey=True)
empl_data.plot(kind='scatter', x='cpi_idx', y='job_growth', ax=axs[0], figsize=(16,8))
empl_data.plot(kind='scatter', x='cpi_index_min_3', y='job_growth', ax=axs[1], figsize=(16,8))
empl_data.plot(kind='scatter', x='cpi_index_min_12', y='job_growth', ax=axs[2], figsize=(16,8))


    

    
Out[107]:





<matplotlib.axes._subplots.AxesSubplot at 0x114df1790>






    

In [80]:

    

# follow the usual sklearn pattern: import, instantiate, fit
from sklearn.linear_model import LinearRegression
slm = LinearRegression()


    

In [108]:

    

list(empl_data.columns.values)


    

    
Out[108]:





['job_growth',
 'job_growth_per',
 'job_growth_min_1',
 'job_growth_min_3',
 'job_growth_min_6',
 'job_growth_min_12',
 'bls_avg_weeks_unemp_per',
 'avg_weeks_unemp',
 'avg_weeks_unemp_min_1',
 'avg_weeks_unemp_min_3',
 'avg_weeks_unemp_min_6',
 'avg_weeks_unemp_min_12',
 'bls_emp_pop_ratio_per',
 'emp_pop_ratio',
 'bls_lbr_frc_prtcp_per',
 'lbr_frc_prtcp',
 'bls_not_in_lbr_frc_thou',
 'not_in_lbr_frc',
 'bls_tot_emp_payrl_thou',
 'totl_emp_payrl',
 'bls_unemp_rate_per',
 'unemp_rate',
 'fed_fund_rate_per',
 'fed_fund_rate',
 '30_yr_fixed_mrtg_per',
 'mortgage_rate',
 'Import_index',
 'import_idx',
 'export_index',
 'export_idx',
 'cpi_index',
 'cpi_idx',
 'cpi_index_min_1',
 'cpi_index_min_3',
 'cpi_index_min_6',
 'cpi_index_min_12',
 'receipts',
 'taxes',
 'taxes_min_1',
 'taxes_min_3',
 'taxes_min_6',
 'taxes_min_12',
 'outlays',
 'spending',
 'spending_min_1',
 'spending_min_3',
 'spending_min_6',
 'spending_min_12']

In [109]:

    

# using scikit-learn
feature_cols = ['job_growth_min_1',
 'job_growth_min_3',
 'job_growth_min_6',
 'job_growth_min_12',
 'avg_weeks_unemp',
 'emp_pop_ratio',
 'lbr_frc_prtcp',
 'not_in_lbr_frc',
 'totl_emp_payrl',
 'unemp_rate',
 'fed_fund_rate',
 'mortgage_rate',
 'cpi_idx',
 'cpi_index_min_1',
 'cpi_index_min_3',
 'cpi_index_min_6',
 'cpi_index_min_12',
 'export_idx',
 'import_idx',
 'taxes',
 'taxes_min_1',
 'taxes_min_3',
 'taxes_min_6',
 'taxes_min_12',
 'spending',
 'spending_min_1',
 'spending_min_3',
 'spending_min_6',
 'spending_min_12']
X = empl_data[feature_cols]
y = empl_data['job_growth']


    

In [110]:

    

slm.fit(X, y)


    

    
Out[110]:





LinearRegression(copy_X=True, fit_intercept=True, normalize=False)

In [111]:

    

slm.score(X,y)


    

    
Out[111]:





0.5590431502011759

In [113]:

    

zip(feature_cols, slm.coef_)


    

    
Out[113]:





[('job_growth_min_1', -0.23909378243307661),
 ('job_growth_min_3', -0.13114668296568571),
 ('job_growth_min_6', -0.13392651685325677),
 ('job_growth_min_12', -0.12080025594343903),
 ('avg_weeks_unemp', 0.064621193212868758),
 ('emp_pop_ratio', 0.28637677532252165),
 ('lbr_frc_prtcp', 0.057200155830819083),
 ('not_in_lbr_frc', 0.00045008377688182379),
 ('totl_emp_payrl', -0.0001126708475896514),
 ('unemp_rate', -0.19343457405120146),
 ('fed_fund_rate', 0.05490460490355735),
 ('mortgage_rate', -0.027500744240230419),
 ('cpi_idx', 0.048283407577361881),
 ('cpi_index_min_1', -0.02727911689107821),
 ('cpi_index_min_3', 0.0045349661610884599),
 ('cpi_index_min_6', 0.0052112519662176233),
 ('cpi_index_min_12', 0.0083427575081458823),
 ('export_idx', -0.047070377573425665),
 ('import_idx', 0.016412300150237324),
 ('taxes', -3.2574437108399086e-07),
 ('taxes_min_1', -2.2888147572807852e-07),
 ('taxes_min_3', -2.6531530003223823e-07),
 ('taxes_min_6', -2.500703304219763e-07),
 ('taxes_min_12', -5.1104027205520154e-08),
 ('spending', -8.39240301799188e-07),
 ('spending_min_1', -3.5962463730133666e-07),
 ('spending_min_3', -2.8156124142869199e-07),
 ('spending_min_6', 5.6857983077750673e-07),
 ('spending_min_12', -2.5692131587383863e-07)]

In [ ]: