def asdi_test():
from models import extended_asdiday as ead
fold = fn.folder_names_init_set()
data_set_name = "InitialTrainingSet_rev1"
cutoff_file = "cutoff_time_list_my_cutoff.csv"
ead.ExtendedASDIDay(fold[0], data_set_name, "training", cutoff_file)
def asdi_test():
from models import extended_asdiday as ead
fold = fn.folder_names_init_set()
data_set_name = "InitialTrainingSet_rev1"
cutoff_file = "cutoff_time_list_my_cutoff.csv"
ead.ExtendedASDIDay(fold[0], data_set_name,
"training", cutoff_file)
def __init__(self, data):
data_set_name = "InitialTrainingSet_rev1"
self.flight_history = pd.DataFrame(None)
self.parsed_fhe = pd.DataFrame(None)
if data == "flight_history":
print "AllTrainingData Initializing: using data {}".format(data)
for f in fn.folder_names_init_set():
print "\tLoading flight_history.csv folder {}...".format(f),
temp = \
pd.read_csv("../Data/" + data_set_name + \
"/" + f + "/" + "FlightHistory/flighthistory.csv",
converters = dut.get_flight_history_date_converter())
self.flight_history = pd.concat([self.flight_history, temp])
print "done"
if data == "parsed_fhe":
print "AllTrainingData Initializing: using data {}".format(data)
for f in fn.folder_names_init_set():
print "\tLoading parsed_fhe.csv file {}...".format(f),
temp = \
pd.read_csv('output_csv/parsed_fhe_' + f + '_' + "all" + '_filtered.csv',
# might have to fix to work with test data?
na_values=["MISSING"], keep_default_na=False,
parse_dates=[9,10,11,12,13,14,15,16,17,18,27,28,29,30,31,32,33,34,35,36,37,38,43,47])
self.parsed_fhe = pd.concat([self.parsed_fhe, temp])
print "done"
if data == "parsed_fhe_test":
print "AllTrainingData Initializing: using data {}".format(data)
for f in fn.folder_names_init_set():
print "\tLoading parsed_fhe.csv file {}...".format(f),
temp = \
pd.read_csv('output_csv/parsed_fhe_' + f + '_' + "test" + '_filtered.csv',
na_values=["MISSING"], keep_default_na=False,
parse_dates=[9,10,11,12,13,14,15,16,17,18,27,28,29,30,31,32,33,34,35,36,37,38,43,47])
self.parsed_fhe = pd.concat([self.parsed_fhe, temp])
print "done"
if data == "parsed_fhe_no_dates":
print "AllTrainingData Initializing: using data {}".format(data)
for f in fn.folder_names_init_set():
print "\tLoading parsed_fhe.csv file {}...".format(f),
temp = \
pd.read_csv('output_csv/parsed_fhe_' + f + '_' + "all" + '_filtered.csv',
# might have to fix to work with test data?
na_values=["MISSING"], keep_default_na=False)
self.parsed_fhe = pd.concat([self.parsed_fhe, temp])
print "done"
if data == "parsed_fhe_test_no_dates":
print "AllTrainingData Initializing: using data {}".format(data)
for f in fn.folder_names_test_set():
print "\tLoading parsed_fhe_test.csv file {}...".format(f),
temp = \
pd.read_csv('output_csv/parsed_fhe_' + f + '_' + "test" + '_filtered.csv',
# might have to fix to work with test data?
na_values=["MISSING"], keep_default_na=False)
self.parsed_fhe = pd.concat([self.parsed_fhe, temp])
print "done"
if data == "parsed_fhe_test_no_dates_with_best":
print "AllTrainingData Initializing: using data {}".format(data)
for f in fn.folder_names_test_set():
print "\tLoading parsed_fhe_test.csv file {}...".format(f),
temp = \
pd.read_csv('output_csv/parsed_fhe_' + f + '_' + "test" + \
'_filtered_with_dates_with_best_prediction.csv',
# might have to fix to work with test data?
na_values=["MISSING"], keep_default_na=False)
self.parsed_fhe = pd.concat([self.parsed_fhe, temp])
print "done"
def run_model(model_A, model_B, data_set_name, mode, cutoff_filename=""):
"""
Runs the most recent update model for each day
in the dataset and returns the result to a
csv file in the python directory.
"""
# Load list of folder names which each contain a day
if data_set_name == "InitialTrainingSet_rev1":
days_list = fn.folder_names_init_set()
elif data_set_name == "PublicLeaderboardSet":
days_list = fn.folder_names_test_set()
else:
days_list = []
print "Problem with data set name!"
# Fin_X contains the final predictions for model X
fin_A = fd.FlightPredictions()
# If we have a second model to compare against, to check for
# improvements or anything like that load it into B
if model_B != None:
fin_B = fd.FlightPredictions()
print "Using mode: {}".format(mode)
print "Using data from {}".format(data_set_name)
# Loop through all of the days in the data set
for i, d in enumerate(days_list):
if model_B == None:
print "Running model '{}' on day {} (day {} of {}):".format(model_A, d, i + 1, len(days_list))
else:
print "Running models '{}', '{}' on day {} (day {} of {}):".format(model_A,
model_B, d, i + 1, len(days_list))
# Initialize all the information about each day.
# Extended means we include the flight history events file
# day = efd.ExtendedFlightDay(d, data_set_name, mode, cutoff_filename)
day = fd.FlightDay(d, data_set_name, mode, cutoff_filename)
# day = ad.ASDIDay(d, data_set_name, mode, cutoff_filename)
# day = ead.ExtendedASDIDay(d, data_set_name, mode, cutoff_filename)
# Compute the predicitons for the day
fin_A = return_predictions(model_A, day, fin_A)
if model_B != None:
fin_B = return_predictions(model_B, day, fin_B)
print "\tDay {} has finished".format(d)
print ""
print "All days in {} are done!".format(data_set_name)
if "leaderboard" in mode:
# In leaderboard mode we just write the predictions to a csv file
# for submission to kaggle
fin_A.flight_predictions = fin_A.flight_predictions.sort(columns='flight_history_id')
fin_A.flight_predictions.to_csv('test.csv', index=False)
print "Predictions written to csv file in Python folder."
if model_B != None:
print "Warning: we have disregarded the output of '{}'!".format(model_B)
elif "training" in mode:
# In training mode we can calculate the root mean squared error as we
# know the true values
score_A = rmse.calculate_rmse_score(fin_A.flight_predictions, fin_A.test_data)
if model_B != None:
score_B = rmse.calculate_rmse_score(fin_B.flight_predictions, fin_B.test_data)
else:
score_B = None
scores = {str(model_A): score_A,
str(model_B): score_B}
# Write the scores to the score log for record keeping
# See if we are making improvements
log_predictions(day, model_A, model_B, scores, "scores.log")
return scores
else:
print "Not an option!"
