def test_analyze_infinite(self):
data = pd.DataFrame({
'A': [2, 4, 5, 6, 8, 9],
'B': [4, 8, float('inf'), 10, 16, 18],
'C': [6, 12, 15, 12, 26, 27]
})
fa = FactorAnalyzer()
fa.analyze(data, 1, impute='drop')
def test_analyze_rotation_value_error(self):
data = pd.DataFrame({
'A': [2, 4, 5, 6, 8, 9],
'B': [4, 8, np.nan, 10, 16, 18],
'C': [6, 12, 15, 12, 26, 27]
})
fa = FactorAnalyzer()
fa.analyze(data, 1, rotation='blah')
def test_analyze_impute_drop(self):
data = pd.DataFrame({
'A': [2, 4, 5, 6, 8, 9],
'B': [4, 8, np.nan, 10, 16, 18],
'C': [6, 12, 15, 12, 26, 27]
})
expected = data.copy()
expected = expected.dropna()
expected_corr = expected.corr()
fa = FactorAnalyzer()
fa.analyze(data, 1, rotation=None, impute='drop')
assert_frame_equal(fa.corr, expected_corr)
def test_factor_variance(self):
path = 'tests/data/test01.csv'
data = pd.read_csv(path)
fa = FactorAnalyzer()
fa.analyze(data, 3, rotation=None)
loadings = fa.loadings
n_rows = loadings.shape[0]
# calculate variance
loadings = loadings**2
variance = loadings.sum(axis=0)
# calculate proportional variance
proportional_variance_expected = variance / n_rows
proportional_variance = fa.get_factor_variance().loc['Proportion Var']
proportional_variance_expected.name = ''
proportional_variance.name = ''
assert_almost_equal(proportional_variance_expected,
proportional_variance)
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)
