y_pred = clf.predict(X)
y_pred = np.asarray(y_pred)
anomalies = np.where(y_pred == 'anomaly')[0]
all_anom.append(DataFrame(data.ix[anomalies]))
if save_models:
joblib.dump(clf, "OneClassSVM_"+str(500+i)+".pkl")
del clf
anom_df = concat(all_anom)
anom_df.to_csv("anomalies_lsq.csv")
if view:
import triangle
from dim_red_vis import dim_red
# Use PCA to look at a projection of the set.
subspace = dim_red(X, verbose=True)
# Do it again with a higher dimension, then project that
subspace = dim_red(X, n_comp=6, verbose=False)
fig = \
triangle.corner(subspace,
labels=['c'+str(i) for i in range(1, 7)])
p.show()
from dim_red_vis import dim_red
execfile(
"/Users/eric/Dropbox/Phys 595/Phys-595/project_code/Machine Learning/hist2d.py"
)
data = read_csv("all_spec_data_cleaned.csv")
X = data[data.columns[1:]]
X = np.asarray(X)
# Standardize the data
X = (X - np.mean(X, axis=0)) / np.std(X, axis=0)
# Use PCA to look at a projection of the set.
subspace = dim_red(X, verbose=False)
hist2d(subspace[:, 0], subspace[:, 1], **{'bins': 10})
# Overplot anomalies on the space
svc_anoms = np.asarray(read_csv("svc_anom_cut.csv")["Unnamed: 0.1"])
p.scatter(subspace[svc_anoms, 0],
subspace[svc_anoms, 1],
c='r',
s=30,
label="SVC Anomalies")
lsq_anoms = np.unique(read_csv("anomalies_lsq.csv")["Unnamed: 0"])
p.scatter(subspace[lsq_anoms, 0],
subspace[lsq_anoms, 1],
c='b',
y_pred = clf.predict(X)
anomalies = np.where(y_pred == -1)[0]
all_anom.append(DataFrame(data.ix[anomalies]))
print "Number of anomalies found: " + str(anomalies.shape)
if save_models:
joblib.dump(clf, "OneClassSVM_" + str(500 + i) + ".pkl")
del clf
anom_df = concat(all_anom)
anom_df.to_csv("anomalies_ocsvm.csv")
if view:
import triangle
from dim_red_vis import dim_red
# Use PCA to look at a projection of the set.
subspace = dim_red(X, verbose=True)
# Do it again with a higher dimension, then project that
subspace = dim_red(X, n_comp=6, verbose=False)
fig = \
triangle.corner(subspace,
labels=['c'+str(i) for i in range(1, 7)])
p.show()
if make_pca:
import triangle
from dim_red_vis import dim_red
execfile("/Users/eric/Dropbox/Phys 595/Phys-595/project_code/Machine Learning/hist2d.py")
data = read_csv("all_spec_data_cleaned.csv")
X = data[data.columns[1:]]
X = np.asarray(X)
# Standardize the data
X = (X - np.mean(X, axis=0))/np.std(X, axis=0)
# Use PCA to look at a projection of the set.
subspace = dim_red(X, verbose=False)
hist2d(subspace[:, 0], subspace[:, 1], **{'bins': 10})
# Overplot anomalies on the space
svc_anoms = np.asarray(read_csv("svc_anom_cut.csv")["Unnamed: 0.1"])
p.scatter(subspace[svc_anoms, 0], subspace[svc_anoms, 1], c='r', s=30,
label="SVC Anomalies")
lsq_anoms = np.unique(read_csv("anomalies_lsq.csv")["Unnamed: 0"])
p.scatter(subspace[lsq_anoms, 0], subspace[lsq_anoms, 1], c='b', s=30,
label="LSQ Anomalies")
both_anoms = np.asarray(list(set(svc_anoms) & set(lsq_anoms)))
p.scatter(subspace[both_anoms, 0], subspace[both_anoms, 1], c='g', s=30,
label="Both")