In [1]:
import pandas as pd

#http://www.eia.gov/coal/

In [3]:
#get directory listing
ls


 Volume in drive C has no label.
 Volume Serial Number is B8DF-9C15

 Directory of C:\Users\Admin\documents\python\rs_explore\dev

12/15/2016  01:44 PM    <DIR>          .
12/15/2016  01:44 PM    <DIR>          ..
12/15/2016  07:33 AM    <DIR>          .ipynb_checkpoints
12/15/2016  01:44 PM             1,627 get_data.ipynb
               1 File(s)          1,627 bytes
               3 Dir(s)   3,762,188,288 bytes free

In [5]:
#what version of pandas
print(pd.__version__)


0.18.1

In [24]:
#get the first data file (use tab to auto complete from list of files)
df1 = pd.read_excel("../data/coalpublic2013.xls",header=2,index_col='MSHA ID')


#check your data frame
df1.head()


Out[24]:
Year Mine Name Mine State Mine County Mine Status Mine Type Company Type Operation Type Operating Company Operating Company Address Union Code Coal Supply Region Production (short tons) Average Employees Labor Hours
MSHA ID
103381 2013 Tacoa Highwall Miner Alabama Bibb Active, men working, not producing Surface Indepedent Producer Operator Mine only Jesse Creek Mining, Llc 1615 Kent Dairy Rd, Alabaster, AL 35007 Appalachia Southern 56004 10 22392
103404 2013 Reid School Mine Alabama Blount Permanently abandoned Surface Indepedent Producer Operator Mine only Taft Coal Sales & Associates, 3000 Riverchase Galleria Ste 1, Birmingham, AL... UNIT Appalachia Southern 28807 18 28447
100759 2013 North River #1 Underground Min Alabama Fayette Active, men working, not producing Underground Indepedent Producer Operator Mine and Preparation Plant Jim Walter Resources Inc 3114 County Rd 63 S, Berry, AL 35546 UNIT Appalachia Southern 1440115 183 474784
103246 2013 Bear Creek Alabama Franklin Active Surface Indepedent Producer Operator Mine only Birmingham Coal & Coke Co., In 912 Edenton Street, Birmingham, AL 35242 Appalachia Southern 87587 13 29193
103451 2013 Knight Mine Alabama Franklin Active Surface Indepedent Producer Operator Mine only Birmingham Coal & Coke Co., In P.O. Box 354, Lynn, AL 35242 Appalachia Southern 147499 27 46393

In [22]:
#get the unique values for Company Type column
df1['Company Type'].unique()


Out[22]:
array(['Indepedent Producer Operator', 'Operating Subsidiary', 'Contractor'], dtype=object)

In [25]:
df1['Company Type'].replace('Indepedent Producer Operator','Independent Producer Operator', inplace=True)

In [26]:
df1.head()


Out[26]:
Year Mine Name Mine State Mine County Mine Status Mine Type Company Type Operation Type Operating Company Operating Company Address Union Code Coal Supply Region Production (short tons) Average Employees Labor Hours
MSHA ID
103381 2013 Tacoa Highwall Miner Alabama Bibb Active, men working, not producing Surface Independent Producer Operator Mine only Jesse Creek Mining, Llc 1615 Kent Dairy Rd, Alabaster, AL 35007 Appalachia Southern 56004 10 22392
103404 2013 Reid School Mine Alabama Blount Permanently abandoned Surface Independent Producer Operator Mine only Taft Coal Sales & Associates, 3000 Riverchase Galleria Ste 1, Birmingham, AL... UNIT Appalachia Southern 28807 18 28447
100759 2013 North River #1 Underground Min Alabama Fayette Active, men working, not producing Underground Independent Producer Operator Mine and Preparation Plant Jim Walter Resources Inc 3114 County Rd 63 S, Berry, AL 35546 UNIT Appalachia Southern 1440115 183 474784
103246 2013 Bear Creek Alabama Franklin Active Surface Independent Producer Operator Mine only Birmingham Coal & Coke Co., In 912 Edenton Street, Birmingham, AL 35242 Appalachia Southern 87587 13 29193
103451 2013 Knight Mine Alabama Franklin Active Surface Independent Producer Operator Mine only Birmingham Coal & Coke Co., In P.O. Box 354, Lynn, AL 35242 Appalachia Southern 147499 27 46393

In [30]:
#replace column heading spaces with underscores
df1.rename(columns=lambda x: x.replace(" ","_"), inplace=True)

In [29]:
df1.head()


Out[29]:
Year Mine_Name Mine_State Mine_County Mine_Status Mine_Type Company_Type Operation_Type Operating_Company Operating_Company_Address Union_Code Coal_Supply_Region Production_(short_tons) Average_Employees Labor_Hours
MSHA ID
103381 2013 Tacoa Highwall Miner Alabama Bibb Active, men working, not producing Surface Independent Producer Operator Mine only Jesse Creek Mining, Llc 1615 Kent Dairy Rd, Alabaster, AL 35007 Appalachia Southern 56004 10 22392
103404 2013 Reid School Mine Alabama Blount Permanently abandoned Surface Independent Producer Operator Mine only Taft Coal Sales & Associates, 3000 Riverchase Galleria Ste 1, Birmingham, AL... UNIT Appalachia Southern 28807 18 28447
100759 2013 North River #1 Underground Min Alabama Fayette Active, men working, not producing Underground Independent Producer Operator Mine and Preparation Plant Jim Walter Resources Inc 3114 County Rd 63 S, Berry, AL 35546 UNIT Appalachia Southern 1440115 183 474784
103246 2013 Bear Creek Alabama Franklin Active Surface Independent Producer Operator Mine only Birmingham Coal & Coke Co., In 912 Edenton Street, Birmingham, AL 35242 Appalachia Southern 87587 13 29193
103451 2013 Knight Mine Alabama Franklin Active Surface Independent Producer Operator Mine only Birmingham Coal & Coke Co., In P.O. Box 354, Lynn, AL 35242 Appalachia Southern 147499 27 46393