Example.txt

#You must load in the module's methods. 
>>> import RandomForestAccountClassification as r

# Create a training object
>>> a = r.FTAC()

# Call the study method on the object. Pass the method as a string that is a directory to your txt or csv file of training #data.

# For more info on how the training and testing data sets should be formatted, consult the readme file. 

>>> a.study('Dir/to/training/set')
>>> import pandas as pd

#create a testing variable.  
>>> test = a.collect('Dir/to/testing/set')
>>> clean_test_reviews = []
>>> clean_test_descriptions = []
>>> num_descriptions = len(test["Description"])
>>> for i in range(0,num_descriptions):
...     if((i+1) % 1000 ==  0 ):
...         print("Review %d of %d\n" % (i+1, num_descriptions))
...     clean_description = a.clean(test['Description'][i])
...     clean_test_descriptions.append(clean_description)

>>> test_data_features = a.v.transform(clean_test_descriptions)
>>> test_data_features = test_data_features.toarray()
>>> result = a.f.predict(test_data_features)
>>> output = pd.DataFrame(data={"id": test["UserID"],
                           "Description": test["Description"],
                           "Personal": result})
#Make sure to write your testing output to a .csv or .txt file (or both). 
>>> output.to_csv('test_output.txt', index = False, quoting = 3)
>>> output.to_csv('test_output.csv', index = False, quoting = 3)