import pandas as pd
import numpy as np
from IPython.display import Markdown, display

def printmd(string, color=None):
    colorstr = "<span style='color:{}'>{}</span>".format(color, string)
    display(Markdown(colorstr))

path_to_compustat='C:\Users\admin\Dropbox\JSRP\data\compustat\a6a9067797a878b4.csv'

CompustatData = pd.read_csv(path_to_compustat)
CompustatData['mcap_alt']=CompustatData['prcc_f']*CompustatData['csho']

naics_labels=['Agriculture, Forestry, Fishing and Hunting',\
        'Mining, Quarrying, and Oil and Gas Extraction',\
        'Utilities',\
        'Construction',\
        'NA1',\
        'Manufacturing',\
        'NA2',\
        'Wholesale Trade',\
        'Retail Trade',\
        'NA3',\
        'Transportation and Warehousing',\
        'NA4',\
        'Information',\
        'Finance and Insurance',\
        'Real Estate and Rental and Leasing',\
        'Professional, Scientific, and Technical Services',\
        'Management of Companies and Enterprises',\
        'Administrative and Support and Waste Management and Remediation Services',\
        'Educational Services',\
        'Health Care and Social Assistance',\
        'Arts, Entertainment, and Recreation',\
        'Accommodation and Food Service',\
        'Other Services','Public administration']


naics_code=[11,21,22,23,24,31,35,42,44,46,48,50,51,52,53,54,55,56,61,62,71,72,81,83,92]
n=24


#naics_labels=['Ag. Mining and Utilities',\
#        'Consts and Mfg',\
#        'Trade and warehousing',\
#        'Information and FIRE',\
#        'RE',\
#        'Professional services',\
#        'Nonprof services']

#naics_code=[11,23,42,51,53,54,57,92]

CompustatData['naics_label']=pd.cut(CompustatData['naics']/104,naics_code[:n+1],labels=naics_labels[:n],include_lowest=True,right=False)
CompustatData['naics_code_cat']=pd.cut(CompustatData['naics']/104,naics_code[:n+1],include_lowest=True,right=False)
CompustatData['naics_2d']=pd.cut(CompustatData['naics']/104,naics_code[:n+1],labels=naics_code[:n],include_lowest=True,right=False)

CompustatData=CompustatData[CompustatData.fyear.notnull()]
CompustatData.fyear=CompustatData.fyear.astype(int)
CompustatData = CompustatData.drop_duplicates(subset = ['gvkey', 'fyear']) #this is not ok.
CompustatData = CompustatData[CompustatData['fic'] == 'USA']

sortcriteria=['sale','pi','mcap_alt']
nlargest=5
industryclassification='naics'
years=[1982,2012]
listbounds=[[211000,212000-1,'naics'],[311000,312000-1,'naics'],[325000,326000-1,'naics'],[336000,336400-1,'naics'],[336400,336500-1,'naics'],[452000,453000-1,'naics'],[484000,485000-1,'naics'],[512000,513000-1,'naics'],[517000,518000-1,'naics'],[522000,523000-1,'naics'],[524000,525000-1,'naics']]

for bounds in listbounds:
    lowerbound=bounds[0]
    upperbound=bounds[1]
    sel_industry=(CompustatData[industryclassification]>=lowerbound)&(CompustatData[industryclassification]<=upperbound)
    printmd(""+ "--------------------------------------------------------------------------------------------------------------"+"")

    printmd(""+industryclassification + ' categories from '+ str(lowerbound)+ ' to '+  str(upperbound)+ ', inclusive'+"")

    for criteria in sortcriteria:
        printmd(""+'Sorted by column: ' + criteria+"")
        for year in years:
            display(CompustatData[( CompustatData['fyear']==year) &sel_industry].nlargest(nlargest,criteria)[['tic','sic','naics','naics_label','conm','fyear','sale','pi','mcap_alt']])