def calculate_py_output(test_name,
factors,
method,
rotation,
top_dir=None):
"""
Use the `FactorAnalyzer()` class to perform the factor analysis
and return a dictionary with relevant output for given scenario.
Parameters
----------
test_name : str
The name of the test
factors : int
The number of factors
method : str
The rotation method
rotation : str
The type of rotation
top_dir : str, optional
The top directory for test data
Defaults to `DATA_DIR``
Returns
-------
output : dict
A dictionary containing the outputs
for all `OUTPUT_TYPES`.
"""
if top_dir is None:
top_dir = DATA_DIR
filename = join(top_dir, test_name + '.csv')
data = pd.read_csv(filename)
rotation = None if rotation == 'none' else rotation
method = {'uls': 'minres'}.get(method, method)
fa = FactorAnalyzer()
fa.analyze(data, factors, method=method, rotation=rotation)
evalues, values = fa.get_eigenvalues()
return {'value': values,
'evalues': evalues,
'structure': fa.structure,
'loading': fa.loadings,
'uniquenesses': fa.get_uniqueness(),
'communalities': fa.get_communalities(),
'scores': fa.get_scores(data)}
def run(self, dfx, n_factors=3):
self.n_factors = n_factors
msg = {}
x_numer_cols, x_cate_cols = ParseDFtypes(dfx)
if x_numer_cols == []:
logging.error(
'All input dfx are no numeric columns, Please check your input dfx data!'
)
msg['error'] = 'All input dfx are no numeric columns, Please check your input dfx data!'
return {'result': pd.DataFrame(), 'msg': msg}
else:
if x_cate_cols != []:
logging.warning(
'input dfx has non-numeric columns: %s, will ignore these columns!'
% x_cate_cols)
msg['warning'] = 'input dfx has non-numeric columns: %s, will ignore these columns!' % x_cate_cols
dfu = dfx[x_numer_cols]
fa = FactorAnalyzer()
fa.analyze(dfu, n_factors, rotation=None)
l = fa.loadings
c = fa.get_communalities()
s = fa.get_scores(dfu)
l.columns = ['因子%s荷载系数' % (i + 1) for i in range(n_factors)]
c.columns = ['共同度']
s.columns = ['因子%s' % (i + 1) for i in range(n_factors)]
res = l.join(c)
return {'result': res, 'msg': msg, 'factor': s}
#Factor loadings fa.loadings # In[22]: #communalities fa.get_communalities() # In[23]: #get_factor_variance fa.get_factor_variance() # In[26]: Fac_score = fa.get_scores(df) # In[27]: print(Fac_score.head()) # # Cluster Analysis using factor scores # In[28]: from sklearn.cluster import KMeans from sklearn.metrics import silhouette_samples, silhouette_score # In[82]: n_clusters = [5, 10, 15, 16, 17, 18, 19, 20, 25, 30]
