parsing with pandas

gistfile1.txt

import pandas as pd
from sklearn import linear_model

file='file1.csv'
df = pd.read_csv(file,
                 header=None,
                 names=['company_id', 'state', 'profit', 'attr1', 'attr2', 'attr3'])

gb = df.groupby(['company_id', 'state'])

for (company_id, state), indicies in gb.groups.items():
    test_set_feature_list     = df.loc[indicies[-2:],'attr1':]
    test_set_label_list       = df.loc[indicies[-2:],'profit']
    training_set_feature_list = df.loc[indicies[:-2],'attr1':]
    training_set_label_list   = df.loc[indicies[:-2],'profit']

    # Create linear regression object
    regr = linear_model.LinearRegression()
    # Train the model using the training sets
    regr.fit(training_set_feature_list, training_set_label_list)

    print (regr.predict(test_set_feature_list))