def undersampling(x, y, ratio=15, xlab=None, xtest=None, ytest=None, ylab=None, lab=None, prefix='', stype="under"):
# 'Random under-sampling'
parameters = {'random_state': 12345, 'max_features': None,
'oob_score': True} # , 'class_weight': 'balanced'}
c = Classifier('rf', parameters, False)
xtrain = x[:, :-1]
# undersampler
US = UnderSampler(ratio=ratio, verbose=False, random_state=12345)
usx, usy = US.fit_transform(x, y)
if not xlab:
xlab = usx[:, -1]
usx = usx[:, :-1]
seuil = threshold_tuning(usx, usy, xlab, title=prefix + 'undersample')
s2 = threshold_tuning(usx, usy, xlab, metric=roc_auc_score,
title=prefix + 'undersample_roc')
s2 = threshold_tuning(usx, usy, xlab, metric=accuracy_score,
title=prefix + 'undersample_acc')
tree = estimator_tree_tuning(
usx, usy, pvalidator=xlab, title=prefix + 'OverSampler_trees')
if xtest is not None:
c.train(usx, usy)
print('====> undersample')
print("------------Result on yeast")
test_and_print(xtest, ytest, ylab, c, seuil)
print("\n------------Result on metazoa")
test_and_print(xtrain, y, lab, c, seuil)
return c
def read_subpop_data(one_hot=True, fake_data=False, test_size=0.2, undersample=False):
labeled_dic = convert_txt_to_npy(LABELED_RL_PATH)
unlabeled_dic = convert_txt_to_npy(UNLABELED_RL_PATH, labeled=False)
X_train, X_test, y_train, y_test = split_train_test(labeled_dic, test_size=test_size)
class DataSets(object):
pass
data_sets = DataSets()
if undersample:
from unbalanced_dataset import UnderSampler
US = UnderSampler(verbose=True)
X_train, y_train = US.fit_transform(X_train, y_train)
lda = LDA()
lda.fit(X_train, y_train)
score = metrics.accuracy_score(lda.predict(X_test), y_test)
print("Baseline LDA: %f " % score)
if one_hot:
y_train = convert_to_one_hot(y_train)
y_test = convert_to_one_hot(y_test)
data_sets = DataSets()
data_sets.test = DataSet(X_test, y_test)
data_sets.train = SemiDataSet(unlabeled_dic['data'], X_train, y_train)
return data_sets
def downsample(d, response, random_state=None, preserve_index=False, verbose=True):
""" Downsample data frame
:param d: Data frame to be downsampled
:param response: Field within data frame to use for downsampling (must contain
only two unique values; an error will be thrown otherwise)
:param random_state: Random state to use for downsampling
:param preserve_index: Determines whether or not the index associated with the given
data frame will be reattached to the downsampled result; if true, the names of all
index fields must be non-null
:param verbose: Flag indicating whether or not summaries of class frequencies should be printed
:return: Data frame idential to "d" with some rows removed, and the values in "response"
occurring with an equal frequency
"""
from unbalanced_dataset import UnderSampler
sampler = UnderSampler(random_state=random_state, replacement=False, verbose=verbose)
idx = None
# If index preservation is requested, store the index field names before reseting it
# on the input data frame (and make sure none of the names are null)
if preserve_index:
assert not np.any(pd.isnull(d.index.names)), \
'When downsampling with "preserve_index=True", index field names must all be non-null. ' \
'At least one name was null for the given index. Index names given: {}'.format(d.index.names)
idx = list(d.index.names)
d = d.reset_index()
# Capture original data frame types and column names
dtypes = d.dtypes.to_dict()
cols = d.columns
# Ensure that the field to be used for downsampling is present
assert response in cols, \
'Given response to use for downsampling "{}" was not found in dataset to be downsampled'.format(response)
# Downsample dataset (as numpy arrays)
ds, _ = sampler.fit_transform(d.values, d[response].values)
# Re-conform resampled frame to original (add cols + index)
d = pd.DataFrame(ds, columns=cols)
for c in d:
d[c] = d[c].astype(dtypes[c])
if preserve_index:
d = d.set_index(idx)
# Return result
return d
def test_rest(x, y):
print('Random under-sampling')
US = UnderSampler(verbose=verbose)
usx, usy = US.fit_transform(x, y)
print('Tomek links')
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
print('Clustering centroids')
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
print('NearMiss-1')
NM1 = NearMiss(version=1, verbose=verbose)
nm1x, nm1y = NM1.fit_transform(x, y)
print('NearMiss-2')
NM2 = NearMiss(version=2, verbose=verbose)
nm2x, nm2y = NM2.fit_transform(x, y)
print('NearMiss-3')
NM3 = NearMiss(version=3, verbose=verbose)
nm3x, nm3y = NM3.fit_transform(x, y)
print('Neighboorhood Cleaning Rule')
NCR = NeighbourhoodCleaningRule(verbose=verbose)
ncrx, ncry = NCR.fit_transform(x, y)
print('Random over-sampling')
OS = OverSampler(verbose=verbose)
ox, oy = OS.fit_transform(x, y)
print('SMOTE Tomek links')
STK = SMOTETomek(verbose=verbose)
stkx, stky = STK.fit_transform(x, y)
print('SMOTE ENN')
SENN = SMOTEENN(verbose=verbose)
sennx, senny = SENN.fit_transform(x, y)
print('EasyEnsemble')
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(x, y)
start = time.time()
Xtrain, Ytrain = GetXY(tableTrain)
end = time.time()
print "Get Train XY Over: ", end - start
# model = LogisticRegression()
# model = RandomForestClassifier(n_estimators=200)
model = GradientBoostingClassifier(n_estimators=300)
# model = AdaBoostClassifier()
start = time.time()
US = UnderSampler(ratio=8.)
# US = ClusterCentroids(ratio=5.)
Xtrain1, Ytrain1 = US.fit_transform(Xtrain, Ytrain)
end = time.time()
print "Data decimation time: ", end - start
start = time.time()
model.fit(Xtrain1, Ytrain1)
joblib.dump(model, modelFilePath + modelFileName)
end = time.time()
print "model train time: ", end - start
# print metrics.classification_report(model.predict(Xtrain), Ytrain)
pYtrain = model.predict_proba(Xtrain)[:, 1]
pYtrain = map(lambda x: 1 if x > 0.4 else 0, pYtrain)
submitNum = sum(pYtrain)
allPosNum = sum(Ytrain)
Yzip = zip(Ytrain, pYtrain)
TPNum = Yzip.count((1, 1))
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from unbalanced_dataset import UnderSampler
from mpl_toolkits.mplot3d import Axes3D
X_reduced=pickle.load(open(sys.argv[1], "rb"))
fileName = sys.argv[2]
X, Y = datasets.load_data(fileName)
# Generate the new dataset using under-sampling method
verbose = False
# 'Random under-sampling'
# ratio of majority elements to sample with respect to the number of minority cases.
US = UnderSampler(ratio=1.,verbose=verbose)
X_reduced, Y = US.fit_transform(X_reduced, Y)
# To getter a better understanding of interaction of the dimensions
# plot the first three tsne dimensions
fig = plt.figure(1, figsize=(8, 6))
ax = Axes3D(fig, elev=-150, azim=110)
ax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2], c=Y, cmap=plt.cm.Paired)
ax.set_title("First three tsne directions")
ax.set_xlabel("1st eigenvector")
ax.w_xaxis.set_ticklabels([])
ax.set_ylabel("2nd eigenvector")
ax.w_yaxis.set_ticklabels([])
ax.set_zlabel("3rd eigenvector")
ax.w_zaxis.set_ticklabels([])
outFile=sys.argv[3]#"pic/tsne_3_t"
fig.savefig(outFile)
X_reduced = pca.fit_transform(X)
# plt.figure(1, figsize=(4, 3))
# plt.clf()
# plt.axes([.2, .2, .7, .7])
# plt.plot(pca.explained_variance_, linewidth=2)
# plt.axis('tight')
# plt.xlabel('n_components')
# plt.ylabel('explained_variance_')
# Generate the new dataset using under-sampling method
verbose = False
# 'Random under-sampling'
# ratio of majority elements to sample with respect to the number of minority cases.
US = UnderSampler(ratio=1., verbose=verbose)
X_reduced, Y = US.fit_transform(X_reduced, Y)
ax.scatter(X_reduced[:, 0],
X_reduced[:, 1],
X_reduced[:, 2],
c=Y,
cmap=plt.cm.Paired)
ax.set_title("First three PCA directions")
ax.set_xlabel("1st eigenvector")
ax.w_xaxis.set_ticklabels([])
ax.set_ylabel("2nd eigenvector")
ax.w_yaxis.set_ticklabels([])
ax.set_zlabel("3rd eigenvector")
ax.w_zaxis.set_ticklabels([])
# outFile3D=sys.argv[2]
# fig.savefig(outFile3D)
def under_sampling(self):
US = UnderSampler(verbose=self.verbose)
usx, usy = US.fit_transform(self.x, self.y)
print "Under Sampling Transformed"
return usx, usy
'mem_requested', 'disk', 'violation'] tain_path = r'/home/askrey/Dropbox/Project_step_by_step/3_create_database/csvs/frull_db_2.csv' X = pd.read_csv(tain_path, header = None, index_col = False ,names = colnames, skiprows = [0], usecols = [3,4,5,6,7]) y = pd.read_csv(tain_path, header = None, index_col = False ,names = colnames, skiprows = [0], usecols = [8]) y = y['violation'].values # X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.333, random_state=0) main_x = X.values main_y = y verbose = False # 'Random under-sampling' US = UnderSampler(verbose=verbose) x, y = US.fit_transform(main_x, main_y) ratio = float(np.count_nonzero(y==1)) / float(np.count_nonzero(y==0)) X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=.333, random_state=0) from sklearn.ensemble import RandomForestClassifier from sklearn.cross_validation import cross_val_score clf = RandomForestClassifier(n_estimators=10) scores = cross_val_score(clf, X_test, y_test) y_pred = clf.fit(X_train, y_train).predict(X_test) y_score = clf.fit(X_train, y_train).predict_proba(X_test)[:,1] prediction, bias, contributions = ti.predict(clf, X_test)
# Plot the original data
# Plot the two classes
plt.scatter(x_vis[y==0, 0], x_vis[y==0, 1], label="Class #0", alpha=0.5,
edgecolor=almost_black, facecolor='red', linewidth=0.15)
plt.scatter(x_vis[y==1, 0], x_vis[y==1, 1], label="Class #1", alpha=0.5,
edgecolor=almost_black, facecolor='blue', linewidth=0.15)
plt.legend()
plt.show()
# Generate the new dataset using under-sampling method
verbose = False
# 'Random under-sampling'
US = UnderSampler(verbose=verbose)
usx, usy = US.fit_transform(x, y)
# 'Tomek links'
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
# 'Clustering centroids'
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
# 'NearMiss-1'
NM1 = NearMiss(version=1, verbose=verbose)
nm1x, nm1y = NM1.fit_transform(x, y)
# 'NearMiss-2'
NM2 = NearMiss(version=2, verbose=verbose)
nm2x, nm2y = NM2.fit_transform(x, y)
# 'NearMiss-3'
NM3 = NearMiss(version=3, verbose=verbose)
nm3x, nm3y = NM3.fit_transform(x, y)
start = time.time()
Xtrain, Ytrain = GetXY(tableTrain)
end = time.time()
print "Get Train XY Over: ", end - start
# model = LogisticRegression()
# model = RandomForestClassifier(n_estimators=200)
model = GradientBoostingClassifier(n_estimators=300)
# model = AdaBoostClassifier()
start = time.time()
US = UnderSampler(ratio=8.)
# US = ClusterCentroids(ratio=5.)
Xtrain1, Ytrain1 = US.fit_transform(Xtrain, Ytrain)
end = time.time()
print "Data decimation time: ", end - start
start = time.time()
model.fit(Xtrain1, Ytrain1)
joblib.dump(model, modelFilePath + modelFileName)
end = time.time()
print "model train time: ", end - start
# print metrics.classification_report(model.predict(Xtrain), Ytrain)
pYtrain = model.predict_proba(Xtrain)[:, 1]
pYtrain = map(lambda x: 1 if x > 0.4 else 0, pYtrain)
submitNum = sum(pYtrain)
allPosNum = sum(Ytrain)
Yzip = zip(Ytrain, pYtrain)
TPNum = Yzip.count((1, 1))
