plt.figure()
colors = ['navy', 'turquoise', 'darkorange']
lw = 2
for color, i, target_name in zip(colors, [0, 1, 2], [0, 1, 2]):
plt.scatter(X_r[y == i, 0],
X_r[y == i, 1],
color=color,
alpha=.8,
lw=lw,
label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('cPCA of IRIS dataset (alpha=2.15)')
plt.show()
ccpca = CCPCA()
ccpca.fit(X[y == 0], X[y != 0], var_thres_ratio=0.5, max_log_alpha=0.5)
X_r2 = ccpca.transform(X)
plt.figure()
for color, i, target_name in zip(colors, [0, 1, 2], [0, 1, 2]):
plt.scatter(X_r2[y == i, 0],
X_r2[y == i, 1],
color=color,
alpha=.8,
lw=lw,
label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('ccPCA of IRIS dataset (alpha =' + str(ccpca.get_best_alpha()) + ')')
plt.show()
def wordCloudGen():
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from ccpca import CCPCA
from opt_sign_flip import OptSignFlip
from mat_reorder import MatReorder
# print("I was here")
# classLabel = request.get.params("label")
dataset_name = request.args.get("datasetName")
print(dataset_name)
data = None
feature_names = None
if ("_updated" in dataset_name):
data = np.loadtxt(open("../data/" + str(dataset_name) + ".csv", "rb"),
delimiter=",",
skiprows=1)
feature_names = np.genfromtxt("../data/" + dataset_name +
".featurenames.csv",
delimiter=",",
dtype='str',
skip_header=1)
else:
data = np.loadtxt(open("./sample_data/" + str(dataset_name) + ".csv",
"rb"),
delimiter=",",
skiprows=1)
feature_names = np.genfromtxt("./sample_data/" + dataset_name +
".featurenames.csv",
delimiter=",",
dtype='str',
skip_header=1)
print(feature_names)
X = None
if ("_updated" in dataset_name):
X = data[:, 1:-3]
else:
X = data[:, :-3]
y = np.int_(data[:, -3])
unique_labels = np.unique(y)
target_label = 0
ccpca = CCPCA(n_components=2)
ccpca.fit(X[y == target_label],
X[y != target_label],
var_thres_ratio=0.5,
n_alphas=40,
max_log_alpha=0.5)
# get results
cpca_result = ccpca.transform(X)
best_alpha = ccpca.get_best_alpha()
cpca_fcs = ccpca.get_feat_contribs()
X = data[:, :-3]
y = np.int_(data[:, -3])
unique_labels = np.unique(y)
_, n_feats = X.shape
n_labels = len(unique_labels)
first_cpc_mat = np.zeros((n_feats, n_labels))
feat_contrib_mat = np.zeros((n_feats, n_labels))
ccpca = CCPCA(n_components=1)
for i, target_label in enumerate(unique_labels):
ccpca.fit(X[y == target_label],
X[y != target_label],
var_thres_ratio=0.5,
n_alphas=40,
max_log_alpha=0.5)
first_cpc_mat[:, i] = ccpca.get_first_component()
feat_contrib_mat[:, i] = ccpca.get_scaled_feat_contribs()
OptSignFlip().opt_sign_flip(first_cpc_mat, feat_contrib_mat)
mr = MatReorder()
mr.fit_transform(feat_contrib_mat)
print(feature_names)
combined = np.vstack((feature_names, cpca_fcs)).T
print(combined)
pd.DataFrame(combined).to_csv("../data/featContrib.csv")
resp = make_response()
resp.headers['Access-Control-Allow-Origin'] = '*'
return resp