def fit(self, BET, target, c=0.1):
from artml.explore import stats
row_indexes = list(BET.index)
target_index = row_indexes.index(target)
BET_features = BET.drop(target, axis=1)
BET_features = BET_features.drop(target, axis=0)
cov_features = stats.covariance(BET_features).values
cov_target = stats.covariance(BET).values
cov_target = cov_target[target_index]
cov_target = np.delete(cov_target, target_index)
I = np.identity(len(cov_features))
inverse = (np.linalg.inv(cov_features) + c * I)
Beta_array = np.matmul(inverse, cov_target)
l = (len(BET))
BET.reset_index(drop=True, inplace=True)
x = BET.to_dict(orient='list')
keys = list(x.keys())
mean_target = (BET[target][keys.index(target)][1]
) / BET[target][keys.index(target)][0]
mean_X = []
for i in range(len(BET_features) + 1):
if i != keys.index(target):
mean_X.append((BET[target][i][1]) / BET[target][i][0])
self.Beta_array = Beta_array
self.intercept_ = mean_target - np.matmul(Beta_array, mean_X)
return (intercept_, Beta_array)
def fit(self, BET, *targets):
l = (len(BET))
BET1 = BET
BET1.reset_index(drop=True, inplace=True)
x = BET1.to_dict(orient='list')
keys = list(x.keys())
mean_ = []
prob_ = []
for target in targets:
mu = []
for i in range(len(BET)):
if keys[i] not in targets:
mu.append((BET[target][i][10]) / BET[target][i][6])
prob_.append(math.log(BET[target][i][6]))
mean_.append(mu)
features = [x for x in BET1.columns if x not in targets]
covaraince_ = stats.covariance(BET)
BET_data = covaraince_.loc[features]
BET_data = BET_data[features]
covaraince_ = BET_data.as_matrix()
self.prob_ = prob_
self.mean_ = mean_
self.covaraince_ = covaraince_
def fit(self, BET):
"""
Principal component analysis (PCA) is a classical statistical method that uses an orthogonal transformation
to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables
called principal components.
Real time Principal components for datasets can be extracted from the ART-M covariance matrix equations.
Examples
--------
PCA(Basic_Element_Table)
This function returns eigen values & eigen vectors for the features in the Basic element table.
"""
from artml.explore import stats
cov = stats.covariance(BET)
cov_mat = cov.values
eig_vals, eig_vecs = np.linalg.eig(cov_mat)
print('Eigenvectors: \n%s' %eig_vecs)
print('\nEigenvalues: \n%s' %eig_vals)
# Make a list of (eigenvalue, eigenvector) tuples
eig_pairs = [(np.abs(eig_vals[i]), eig_vecs[:,i]) for i in range(len(eig_vals))]
# Sort the (eigenvalue, eigenvector) tuples from high to low
eig_pairs.sort(key=lambda x: x[0], reverse=True)
# Visually confirm that the list is correctly sorted by decreasing eigenvalues
print('\nEigenvalues in descending order:')
for i in eig_pairs:
print(i[0])