-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Script and results of calculating marginal efects (derivative) for kn…
…owledge and skills indicator for all 3-digit NAICS categories. Useful for building scenarios #5
- Loading branch information
Showing
2 changed files
with
167 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,80 @@ | ||
import pandas as pd | ||
import numpy as np | ||
import joblib | ||
import os | ||
from innovation_indicator import InnoIndicator | ||
from indicator_tools import DataLoader | ||
from APICalls import CBPCall | ||
|
||
def industry_to_skills_knowledge(Xdiff,I): | ||
industry_compositions = Xdiff.to_dict('records') | ||
skill_compositions = [] | ||
knowledge_compositions = [] | ||
for industry_composition in industry_compositions: | ||
worker_composition = I.industries_to_occupations(industry_composition) | ||
skill_composition = I.occupations_to_skills(worker_composition) | ||
knowledge_composition = I.occupations_to_knowledge(worker_composition) | ||
skill_compositions.append(skill_composition) | ||
knowledge_compositions.append(knowledge_composition) | ||
return skill_compositions,knowledge_compositions | ||
|
||
def AME_industry(I,col,X): | ||
''' | ||
Numbers should be interpreted as the change in the average indicator (over all X) as a result of a 0.1 increase in the given NAICS code | ||
''' | ||
dx = np.median(np.diff(sorted(X[X[col]!=0][col]))) | ||
|
||
X_ = X.reset_index().drop('index',1) | ||
X_[col] = X[col]+dx | ||
Xdiff = pd.concat([X.reset_index().drop('index',1),X_]).sort_index().sort_values(by=col).sort_index() | ||
|
||
skill_compositions,knowledge_compositions = industry_to_skills_knowledge(Xdiff,I) | ||
|
||
Ypred = I.sks_model.predict(pd.DataFrame(skill_compositions)) | ||
if I.normalize: | ||
Ypred = I.normalize_value(Ypred,I.sks_bounds) | ||
dsks = np.diff(Ypred)[::2] | ||
dsksdx = (dsks/dx)*0.1 | ||
|
||
Ypred = I.kno_model.predict(pd.DataFrame(knowledge_compositions)) | ||
if I.normalize: | ||
Ypred = I.normalize_value(Ypred,I.kno_bounds) | ||
dkno = np.diff(Ypred)[::2] | ||
dknodx = (dkno/dx)*0.1 | ||
|
||
return np.mean(dsksdx),np.mean(dknodx) | ||
|
||
def main(): | ||
outPath = 'tables/innovation_data' | ||
outfpath = os.path.join(outPath,'innovation_marginal_effect.csv') | ||
if os.path.isfile(outfpath): | ||
print('Marginal effects already stored. To recompute, delete the current results located at: {}'.format(outfpath)) | ||
else: | ||
print('Loading indicator and employment by industry for each MSA') | ||
I = InnoIndicator() | ||
|
||
data = DataLoader() | ||
data.load_MSA_emp_byInd() | ||
|
||
X = pd.pivot_table(data.emp_msa_ind,values='EMP',index='MSA',columns='NAICS2017').fillna(0) | ||
X = X.assign(TOTAL=X.sum(1)) | ||
for c in set(data.emp_msa_ind['NAICS2017']): | ||
X[c] = X[c]/X['TOTAL'] | ||
X = X.drop('TOTAL',1) | ||
X = X.reset_index().drop('MSA',1) | ||
|
||
kno_ames = {} | ||
sks_ames = {} | ||
for col in X.columns: | ||
print('\tDerivating with respect to NAICS: {}'.format(col)) | ||
sks_ame,kno_ame = AME_industry(I,col,X) | ||
sks_ames[col] = sks_ame | ||
kno_ames[col] = kno_ame | ||
|
||
print('Combining and saving results') | ||
ames = pd.DataFrame(sks_ames.items(),columns=['NAICS','SKS_AME']) | ||
ames = pd.merge(ames,pd.DataFrame(kno_ames.items(),columns=['NAICS','KNO_AME'])) | ||
ames.to_csv(outfpath,index=False) | ||
|
||
if __name__ == '__main__': | ||
main() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,87 @@ | ||
NAICS,SKS_AME,KNO_AME | ||
113,-0.0010081329749168442,0.0008215616681947015 | ||
114,0.0,0.0 | ||
115,0.005331352440146175,0.011326441277018682 | ||
211,-0.0015025807533984355,0.0008727175479176082 | ||
212,-0.00035925773436701986,-0.0007390407141070343 | ||
213,0.0004994676691068528,-0.0012624333154087786 | ||
221,0.0012717248107538392,0.0021578503881758003 | ||
236,-0.0009218064507108101,0.004056471430585033 | ||
237,-0.0036318999212354964,-0.004087177913570991 | ||
238,0.00012192234318997239,0.0014465750123501494 | ||
311,-0.0007920641135756543,0.00048727517217120444 | ||
312,0.0006912557924184535,0.000378877323935994 | ||
313,-0.0008681383864413026,-0.0007415169340151791 | ||
314,0.002605409338321021,0.00029021347961229687 | ||
315,0.0008351872401136031,-0.0004995439730953404 | ||
316,-0.00037784841909284795,0.0006462865831488685 | ||
321,0.0007712254688466172,0.0013748053406052701 | ||
322,-0.0005742015711983488,0.0001301004731152185 | ||
323,-0.0021770199500289887,-0.0014374384276624195 | ||
324,-0.0009020907222388108,0.0021950026169347612 | ||
325,0.0005900995245826787,5.6282859756566593e-05 | ||
326,-0.004050443400593441,0.0022943663727317213 | ||
327,-0.0011019174308332397,0.0002722640345279 | ||
331,0.0021785895005027142,-0.003180449721115953 | ||
332,0.0006309533853245033,-0.0012011461747499944 | ||
333,-0.0006700880509807163,0.00033729078076171696 | ||
334,0.009457699998955588,0.0026595338159675014 | ||
335,-6.812186507010933e-05,0.0001505735932133951 | ||
336,0.002684985253620547,-0.0004346476796265838 | ||
337,-0.0022194235070368733,0.0007283928577279558 | ||
339,0.00024657115478763796,0.0004552130679293148 | ||
423,0.000980348626829013,-0.00012240419634919995 | ||
424,0.0028585031860447244,-0.0013640729501855245 | ||
425,-0.0006581477579017459,0.0029901973101106594 | ||
441,-0.005120459202580126,-0.00017373417425580956 | ||
442,-0.005579793646584501,-0.0007661136789298016 | ||
443,0.002831436438755288,0.0005804020987567821 | ||
444,-0.002325733263611379,-0.0004236978234214252 | ||
445,0.0007450184549293255,-8.560687701874633e-05 | ||
446,0.001976017961614613,0.0008976078209224188 | ||
447,-0.0027217517949322165,-3.31348299158954e-06 | ||
448,-0.0002201055404436805,-0.0018945687511926143 | ||
451,0.0034184030449191725,0.0005028724194009636 | ||
452,0.0010993939752942585,0.0005838967574243104 | ||
453,-0.00021441928545249086,-0.0008171131682508174 | ||
454,-0.001509811042408386,0.000667948223966807 | ||
481,1.0731470969637641e-05,0.0008036746906909888 | ||
483,-0.0010180284170084053,-0.00029025819656784273 | ||
484,-0.0009932937403081285,-0.00021835355195150565 | ||
485,-0.005140368085304926,0.0028584966190532885 | ||
486,0.00017445928210434923,-0.0017348955172126709 | ||
487,0.00034084211476076643,-0.0001860268444278296 | ||
488,7.136969839214075e-06,-1.3012943242055966e-05 | ||
492,0.002940692225247223,0.0009131003130846011 | ||
493,-0.0017003402156584688,-0.0004919760811171008 | ||
511,0.006545675562925853,0.005209444915301953 | ||
512,0.0018400022425876976,0.00022118277593453534 | ||
515,-0.0007572938394203913,0.0001905167884248805 | ||
517,0.003780290065944719,0.0018535698429968611 | ||
518,0.007066267626448401,0.0017205707794635619 | ||
519,0.006340530962522851,0.004909676217487644 | ||
521,, | ||
522,0.002989881333536439,-0.0006263415090439653 | ||
523,0.010117050315383371,0.005179954710735036 | ||
524,0.005970379078332785,0.005942656964698942 | ||
525,-0.0024746912944443164,-0.002492728085617204 | ||
531,-0.0026761308198427246,0.0011065176571430641 | ||
532,0.003057936791174244,-0.0002578914690973307 | ||
533,-0.0014302442826843874,-0.001626236364408166 | ||
541,0.004129255635239373,0.004002397453786828 | ||
551,0.0015038042996112022,0.0019835075020518487 | ||
561,0.0007125317435620928,0.00027453783165628734 | ||
562,0.00046792847602607305,-5.6425724486557e-06 | ||
611,-0.004514909849051968,0.00417515804167604 | ||
621,-0.003462907993533807,0.0004542386953435541 | ||
622,0.0017909137203057617,-0.00041915996973275146 | ||
623,-0.0006887317918564533,-8.012582147660481e-05 | ||
624,0.0034739200696393283,-0.0005142657021886784 | ||
711,0.0030895218866598744,-0.0002975022669487763 | ||
712,0.0017882313496743,0.0008387966154144958 | ||
713,1.3569027570167881e-05,0.0001124705443953574 | ||
721,5.3942584788079756e-05,-0.0008892446534328178 | ||
722,-0.006038700331290567,-0.00035115379473005774 | ||
811,0.0009701240128918857,0.0006104933376387998 | ||
812,0.0021436587241087197,0.0023389056259735786 | ||
813,-0.002415677049105057,-0.0036722262871510857 |