def run():
# prepare data
util_file.prepare_file(configuration.data_file)
# read prepared data
dataset = pd.read_csv(configuration.data_file_cleaned)
# creating random forest
create_random_forests(dataset)
def run():
# prepare data
util_file.prepare_file(configuration.data_file)
# read prepared data
dataset = pd.read_csv(configuration.data_file_cleaned)
# check correlation
correlations = util.check_correlation(dataset, configuration.dimensions)
print("correlations:", correlations)
def run():
# prepare data
util_file.prepare_file(configuration.data_file)
# read prepared data
dataset = pd.read_csv(configuration.data_file_cleaned)
# check correlation
#correlations = util.check_correlation(dataset, configuration.dimensions_pol)
#print("correlations:", correlations)
# generate linear models and calculate their metrics
generate_models(configuration.dimensions_logregpca, dataset)
def run():
print("running contentbased algorithm")
# prepare data
util_file.prepare_file(configuration.data_file)
# read prepared data
dataset = pd.read_csv(configuration.data_file_cleaned)
for threshold in range(1,100):
calculateAllProfiles(dataset, threshold)
print(results)
results.to_csv("content_based_results.csv")
def runParTuning():
# prepare data
util_file.prepare_file(configuration.data_file)
# read prepared data
dataset = pd.read_csv(configuration.data_file_cleaned)
for dep in configuration.dependent:
print("running parameter tuning maxdepth for :", dep)
partun_max_depth(dataset, dep)
# parameter tuning
for dep in configuration.dependent:
print("running parameter tuning n_estimators for :", dep)
partun_n_estimators(dataset, dep)