def runFactorAnalyzer(self, cols_to_norm, result):
fa = FactorAnalyzer(rotation="varimax", n_factors=2)
df = result[cols_to_norm]
result = result.dropna()
df = df.dropna()
fa.fit(df)
ev = fa.get_eigenvalues()
kmo_all, kmo_model = calculate_kmo(df)
if (kmo_model < 0.6):
print("kmo_model: %s " % kmo_model)
array = fa.transform(df)
#print("Factors: %s" % (array))
#print("loadings: %s " % fa.loadings_)
#print("eigenvalues: %s " % ev[0])
dataframe = pd.DataFrame(columns=[
'Player', 'Session', 'Time', 'NegativeEmotion', 'PositiveEmotion'
])
print("T session: %s " % len(result['Session']))
dataframe['Session'] = result['Session']
dataframe['Player'] = result['Player']
dataframe['Time'] = result['ts']
dataframe['NegativeEmotion'] = np.around(array[:, 0], 2)
dataframe['PositiveEmotion'] = np.around(array[:, 1], 2)
dataframe.to_csv('/home/elton/Desktop/Dataset/MetricsEmotion.csv',
sep=',',
mode='a',
header=False)
def get_factor_eigenvalues(df):
fa = FactorAnalyzer(rotation=None)
fa.fit(df)
ev, v = fa.get_eigenvalues()
return ev
def main():
""" Run the script.
"""
# set up an argument parser
parser = argparse.ArgumentParser(prog='factor_analyzer.py')
parser.add_argument(
dest='feature_file',
help="Input file containing the pre-processed features "
"for the training data")
parser.add_argument(
dest='output_dir',
help="Output directory to save "
"the output files",
)
parser.add_argument('-f',
'--factors',
dest="num_factors",
type=int,
default=3,
help="Number of factors to use (Default 3)",
required=False)
parser.add_argument('-r',
'--rotation',
dest="rotation",
type=str,
default='none',
help="The rotation to perform (Default 'none')",
required=False)
parser.add_argument('-m',
'--method',
dest="method",
type=str,
default='minres',
help="The method to use (Default 'minres')",
required=False)
# parse given command line arguments
args = parser.parse_args()
method = args.method
factors = args.num_factors
rotation = None if args.rotation == 'none' else args.rotation
file_path = args.feature_file
if not file_path.lower().endswith('.csv'):
raise ValueError('The feature file must be in CSV format.')
data = pd.read_csv(file_path)
# get the logger
logger = logging.getLogger(__name__)
logging.setLevel(logging.INFO)
# log some useful messages so that the user knows
logger.info(
"Starting exploratory factor analysis on: {}.".format(file_path))
# run the analysis
analyzer = FactorAnalyzer()
analyzer.analyze(data, factors, rotation, method)
# create paths to loadings loadings, eigenvalues, communalities, variance
path_loadings = os.path.join(args.output_dir, 'loadings.csv')
path_eigen = os.path.join(args.output_dir, 'eigenvalues.csv')
path_communalities = os.path.join(args.output_dir, 'communalities.csv')
path_variance = os.path.join(args.output_dir, 'variance.csv')
# retrieve loadings, eigenvalues, communalities, variance
loadings = analyzer.loadings
eigen, _ = analyzer.get_eigenvalues()
communalities = analyzer.get_communalities()
variance = analyzer.get_factor_variance()
# save the files
logger.info("Saving files...")
loadings.to_csv(path_loadings)
eigen.to_csv(path_eigen)
communalities.to_csv(path_communalities)
variance.to_csv(path_variance)
