def blogcatalog_test_scenario(deepwalk_path):
y_path = '../../local_resources/blogcatalog/y.p'
x_path = '../../local_resources/blogcatalog/X.p'
target = utils.read_target(y_path)
x, y = utils.read_data(x_path, y_path, threshold=0)
names = [['deepwalk'], ['logistic']]
x_deepwalk = pd.read_csv(deepwalk_path, index_col=0)
# all_features = np.concatenate((x.toarray(), x_deepwalk), axis=1)
X = [x_deepwalk.values, normalize(x, axis=0)]
n_folds = 10
results = run_detectors.run_all_datasets(X, y, names, classifiers, n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('../../results/karate/deepwalk_macro_pvalues' +
utils.get_timestamp() + '.csv')
tests[1].to_csv('../../results/karate/deepwalk_micro_pvalues' +
utils.get_timestamp() + '.csv')
print('macro', results[0])
print('micro', results[1])
macro_path = '../../results/karate/deepwalk_macro' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/karate/deepwalk_micro' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def blogcatalog_deepwalk_node2vec():
paths = [
'local_resources/blogcatalog/blogcatalog128.emd',
'local_resources/blogcatalog/blogcatalog_p025_q025_d128.emd'
]
names = [['logistic_p1_q1'], ['logistic_p025_q025']]
y_path = 'local_resources/blogcatalog/y.p'
detectors = [classifiers_embedded_128, classifiers_embedded_128]
sizes = [128, 128]
X, y = read_embeddings(paths, y_path, sizes)
n_folds = 5
results = run_all_datasets(X, y, names, detectors, n_folds)
all_results = utils.merge_results(results)
results = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = 'results/blogcatalog/macro_deepwalk_node2vec' + utils.get_timestamp(
) + '.csv'
micro_path = 'results/blogcatalog/micro_deepwalk_node2vec' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def test_embeddings():
feature_path = '../local_resources/features_1in10000.tsv'
rf_features = pd.read_csv(feature_path, sep='\t', index_col=0)
emd = pd.read_csv('../local_resources/hyperbolic_embeddings/tf_test1.csv',
header=None,
index_col=0,
skiprows=1,
sep=" ")
features, y = utils.get_classification_xy(rf_features)
features = features.loc[emd.index, :]
y = y.loc[emd.index].values
names = np.array([['RF just emd']])
n_folds = 10
classifiers = [
RandomForestClassifier(max_depth=2,
n_estimators=50,
bootstrap=True,
criterion='entropy',
max_features=0.1,
n_jobs=1)
]
results = run_all_datasets([emd.values], y, names, classifiers, n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = 'tf_testing_1in10000' + utils.get_timestamp() + '.csv'
micro_path = 'tf_micro_1in10000' + utils.get_timestamp() + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
assert results[0]['mean'].values > 0.6
def blogcatalog_121_scenario(embedding_path):
target_path = '../../local_resources/blogcatalog_121_sample/y.p'
feature_path = '../../local_resources/blogcatalog_121_sample/X.p'
hyperbolic = pd.read_csv(embedding_path, index_col=0).values
paths = ['../../local_resources/blogcatalog_121_sample/blogcatalog2.emd']
sizes = [128]
[deepwalk], y = read_embeddings(paths, target_path, sizes)
names = [['logistic'], ['deepwalk'], ['hyp embedding']]
x = utils.read_pickle(feature_path)
# y = utils.read_pickle(target_path)
X = [x, deepwalk, hyperbolic]
n_folds = 2
results = run_all_datasets(X, y, names, classifiers, n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = '../../results/blogcatalog_121_sample/macro' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/blogcatalog_121_sample/micro' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def karate_scenario():
deepwalk_path = 'local_resources/zachary_karate/size8_walks1_len10.emd'
y_path = 'local_resources/zachary_karate/y.p'
x_path = 'local_resources/zachary_karate/X.p'
target = utils.read_target(y_path)
x, y = utils.read_data(x_path, y_path, threshold=0)
names = [['logistic'], ['deepwalk']]
x_deepwalk = utils.read_embedding(deepwalk_path, target)
# all_features = np.concatenate((x.toarray(), x_deepwalk), axis=1)
X = [x_deepwalk, normalize(x, axis=0)]
n_folds = 2
results = run_all_datasets(X, y, names, classifiers, n_folds)
all_results = utils.merge_results(results)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('results/karate/deepwalk_macro_pvalues' +
utils.get_timestamp() + '.csv')
tests[1].to_csv('results/karate/deepwalk_micro_pvalues' +
utils.get_timestamp() + '.csv')
print 'macro', results[0]
print 'micro', results[1]
macro_path = 'results/karate/deepwalk_macro' + utils.get_timestamp(
) + '.csv'
micro_path = 'results/karate/deepwalk_micro' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def tf_train100000_emd_scenario():
scaler = StandardScaler()
feature_path = '../../local_resources/features_train100000.tsv'
# feature_path = '../../local_resources/features_train100000.tsv'
rf_features = pd.read_csv(feature_path, sep='\t', index_col=0)
del rf_features.index.name
emd = pd.read_csv('../../local_results/tf_train_100000.emd',
header=None,
index_col=0,
skiprows=1,
sep=" ")
# emd = pd.read_csv('../../local_results/tf_train_100000.emd', header=None, index_col=0, skiprows=1, sep=" ")
features, y = utils.get_classification_xy(feature_path, emd)
all_feat = features.join(emd)
X1 = features.values.astype(np.float)
X1 = scaler.fit_transform(X1)
X2 = all_feat.values.astype(np.float)
X2 = scaler.fit_transform(X2)
names = np.array([['L2 without emd', 'L1 without emd', 'RF without emd'],
['L2 with emd', 'L1 with emd', 'RF with emd'],
['L2 just emd', 'L1 just emd', 'RF just emd']])
n_folds = 10
results = run_all_datasets([X1, X2, emd.values], y, names, classifiers,
n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = '../../results/neural/tf_macro_train100000' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/neural/tf_micro_train100000' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def batch_size_scenario():
"""
Generate embeddings using different batch sizes for the ~1000 vertex polblogs network
:return:
"""
import visualisation
s = datetime.datetime.now()
y_path = '../../local_resources/political_blogs/y.p'
x_path = '../../local_resources/political_blogs/X.p'
y = utils.read_pickle(y_path)
log_path = '../../local_resources/tf_logs/polblogs/'
walk_path = '../../local_resources/political_blogs/walks_n1_l10.csv'
size = 2 # dimensionality of the embedding
batch_sizes = [1, 2, 4, 8, 16, 32, 64, 128]
embeddings = []
for batch_size in batch_sizes:
params = Params(walk_path, batch_size=batch_size, embedding_size=size, neg_samples=5, skip_window=5,
num_pairs=1500,
statistics_interval=10.0,
initial_learning_rate=0.1, save_path=log_path, epochs=5, concurrent_steps=4)
path = '../../local_resources/political_blogs/embeddings/Win_batch_{}_{}.csv'.format(
batch_size, utils.get_timestamp())
embedding_in, embedding_out = HCE.main(params)
visualisation.plot_poincare_embedding(embedding_in, y,
'../../results/political_blogs/figs/poincare_polar_Win_batch_{}_{}.pdf'.format(
batch_size, utils.get_timestamp()))
visualisation.plot_poincare_embedding(embedding_out, y,
'../../results/political_blogs/figs/poincare_polar_Wout_batch_{}_{}.pdf'.format(
batch_size, utils.get_timestamp()))
df_in = pd.DataFrame(data=embedding_in, index=np.arange(embedding_in.shape[0]))
df_in.to_csv(path, sep=',')
df_out = pd.DataFrame(data=embedding_out, index=np.arange(embedding_out.shape[0]))
df_out.to_csv(
'../../local_resources/political_blogs/embeddings/Wout_batch_{}_{}.csv'.format(
batch_size, utils.get_timestamp()),
sep=',')
print('political blogs embedding generated in: ', datetime.datetime.now() - s)
embeddings.append(embedding_in)
x, y = utils.read_data(x_path, y_path, threshold=0)
names = [[str(batch_size)] for batch_size in batch_sizes]
n_folds = 10
results = run_detectors.run_all_datasets(embeddings, y, names, classifiers, n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('../../results/political_blogs/batch_size_pvalues' + utils.get_timestamp() + '.csv')
tests[1].to_csv('../../results/political_blogs/batch_size_pvalues' + utils.get_timestamp() + '.csv')
print('macro', results[0])
print('micro', results[1])
macro_path = '../../results/political_blogs/batch_size_macro' + utils.get_timestamp() + '.csv'
micro_path = '../../results/political_blogs/batch_size_micro' + utils.get_timestamp() + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
return path
def gensim_1in10000_emd_scenario():
scaler = StandardScaler()
feature_path = '../../local_resources/features_1in10000.tsv'
rf_features = pd.read_csv(feature_path, sep='\t', index_col=0)
emd = pd.read_csv('../../local_results/customer.emd',
header=None,
index_col=0,
skiprows=1,
sep=" ")
features, y = utils.get_classification_xy(rf_features)
# select only the data points that we have embeddings for
features = features.loc[emd.index, :]
y = y.loc[emd.index].values
all_feat = features.join(emd, how='inner')
print 'input features shape', all_feat.shape
X1 = features.values.astype(np.float)
X1 = scaler.fit_transform(X1)
X2 = all_feat.values.astype(np.float)
X2 = scaler.fit_transform(X2)
# names = np.array(
# [['L2 without emd'], ['L2 with emd']])
names = np.array([['L2 without emd'], ['L2 with emd'], ['L2 just emd']])
# names = np.array(
# [['L2 without emd', 'L1 without emd', 'RF without emd'], ['L2 with emd', 'L1 with emd', 'RF with emd'],
# ['L2 just emd', 'L1 just emd', 'RF just emd']])
# names = np.array([['without MF'], ['with MF']])
n_folds = 5
# np.random.seed(42)
clf = LogisticRegression(multi_class='ovr',
penalty='l2',
solver='liblinear',
n_jobs=1,
max_iter=1000,
C=0.005)
df = run_repetitions([X1, X2, emd.values], y, clf, names, reps=10)
print df
# results = run_all_datasets([X1, X2], y, names, [clf], n_folds)
results = run_all_datasets([X1, X2, emd.values], y, names, classifiers,
n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = '../../results/neural/gensim_1in10000' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/neural/gensim_1in10000' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def karate_deepwalk_grid_scenario():
"""
evaluates a grid of embeddings at different sizes, walk lengths and walks per vertex for the karate network.
Trying to understand why the DeepWalk performance was so poor.
:return:
"""
import os
y_path = '../../local_resources/karate/y.p'
x_path = '../../local_resources/karate/X.p'
target = utils.read_target(y_path)
x, y = utils.read_data(x_path, y_path, threshold=0)
folder = '../../local_resources/karate/gridsearch/'
names = [[elem] for elem in os.listdir(folder)]
embeddings = []
for name in names:
emb = pd.read_csv(folder + name[0],
header=None,
index_col=0,
skiprows=1,
sep=" ")
emb.sort_index(inplace=True)
embeddings.append(emb.values)
names.append(['hyperbolic'])
hyp_path = '../../local_resources/karate/embeddings/Win_20170808-185202.csv'
hyp_emb = pd.read_csv(hyp_path, index_col=0)
embeddings.append(hyp_emb.values)
n_folds = 10
results = run_detectors.run_all_datasets(embeddings, y, names, classifiers,
n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('../../results/karate/pvalues' + utils.get_timestamp() +
'.csv')
tests[1].to_csv('../../results/karate/pvalues' + utils.get_timestamp() +
'.csv')
print('macro', results[0])
print('micro', results[1])
macro_path = '../../results/karate/macro' + utils.get_timestamp() + '.csv'
micro_path = '../../results/karate/micro' + utils.get_timestamp() + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def MF_scenario():
scaler = StandardScaler()
feature_path = '../../local_resources/features_1in10000.tsv'
rf_features = pd.read_csv(feature_path, sep='\t', index_col=0)
del rf_features.index.name
emd = pd.read_csv('../../local_resources/roberto_emd.csv',
header=None,
index_col=0)
del emd.index.name
# emd = reduce_embedding(emd)
# filter the features by customer ID
temp = rf_features.join(emd[1], how='inner')
features = temp.drop(1, axis=1)
# extract the churn target labels
print 'class distribution', features['target_churned'].value_counts()
y = features['target_churned'].values.astype(int)
# remove the labels
features = features.ix[:, :-4]
# encode the categoricals
features['shippingCountry'] = utils.convert_to_other(
features['shippingCountry'], pct=0.05, label='Other')
features = pd.get_dummies(features, columns=['shippingCountry', 'gender'])
all_feat = features.join(emd)
X1 = features.values.astype(np.float)
X1 = scaler.fit_transform(X1)
X2 = all_feat.values.astype(np.float)
X2 = scaler.fit_transform(X2)
names = np.array([['L2 without MF', 'L1 without MF', 'RF without MF'],
['L2 with MF', 'L1 with MF', 'RF with MF'],
['L2 just MF', 'L1 just MF', 'RF just MF']])
# names = np.array([['without MF'], ['with MF']])
n_folds = 20
results = run_all_datasets([X1, X2, emd.values], y, names, classifiers,
n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = '../../results/MF/macro_1of100000no_cat' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/MF/micro_1of100000no_cat' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def karate_results(embeddings, names, n_reps, train_size):
deepwalk_path = '../../local_resources/zachary_karate/size8_walks1_len10.emd'
y_path = '../../local_resources/zachary_karate/y.p'
x_path = '../../local_resources/zachary_karate/X.p'
target = utils.read_target(y_path)
x, y = utils.read_data(x_path, y_path, threshold=0)
# names = [['embedding'], ['logistic']]
names.append(['logistics'])
# x_deepwalk = utils.read_embedding(deepwalk_path, target)
# all_features = np.concatenate((x.toarray(), x_deepwalk), axis=1)
# X = [normalize(embedding, axis=0), normalize(x, axis=0)]
X = embeddings + [normalize(x, axis=0)]
# names = ['embedding']
# X = embedding
results = []
for exp in zip(X, names):
tmp = run_detectors.run_experiments(exp[0], y, exp[1], classifiers,
n_reps, train_size)
results.append(tmp)
all_results = utils.merge_results(results, n_reps)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('../../results/karate/tf_macro_pvalues' +
utils.get_timestamp() + '.csv')
tests[1].to_csv('../../results/karate/tf_micro_pvalues' +
utils.get_timestamp() + '.csv')
print('macro', results[0])
print('micro', results[1])
macro_path = '../../results/karate/tf_macro' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/karate/tf_micro' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
return results
def political_blogs_scenario(embedding_path):
# deepwalk_path = '../../local_resources/hyperbolic_embeddings/tf_test1.csv'
y_path = '../../local_resources/political_blogs/y.p'
x_path = '../../local_resources/political_blogs/X.p'
sizes = [2, 4, 8, 16, 32, 64, 128]
deepwalk_embeddings = []
deepwalk_names = []
dwpath = '../../local_resources/political_blogs/political_blogs'
for size in sizes:
path = dwpath + str(size) + '.emd'
de = pd.read_csv(path, header=None, index_col=0, skiprows=1, sep=" ")
de.sort_index(inplace=True)
deepwalk_embeddings.append(de.values)
deepwalk_names.append(['deepwalk' + str(size)])
x, y = utils.read_data(x_path, y_path, threshold=0)
names = [['hyperbolic'], ['logistic']]
names = deepwalk_names + names
embedding = pd.read_csv(embedding_path, index_col=0)
# all_features = np.concatenate((x.toarray(), x_deepwalk), axis=1)
X = deepwalk_embeddings + [embedding.values, normalize(x, axis=0)]
n_folds = 10
results = run_detectors.run_all_datasets(X, y, names, classifiers, n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('../../results/political_blogs/pvalues' +
utils.get_timestamp() + '.csv')
tests[1].to_csv('../../results/political_blogs/pvalues' +
utils.get_timestamp() + '.csv')
print('macro', results[0])
print('micro', results[1])
macro_path = '../../results/political_blogs/macro' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/political_blogs/micro' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def gensim_1in10000_debug_scenario():
scaler = StandardScaler()
feature_path = '../../local_resources/features_1in10000.tsv'
rf_features = pd.read_csv(feature_path, sep='\t', index_col=0)
del rf_features.index.name
print 'input features shape', rf_features.shape
emd = pd.read_csv('../../local_results/customer.emd',
header=None,
index_col=0,
skiprows=1,
sep=" ")
print 'input embedding shape', rf_features.shape
# emd = pd.read_csv('../../local_results/customer.emd', header=None, index_col=0, skiprows=1, sep=" ")
features, y = utils.get_classification_xy(feature_path, emd)
assert len(features) == features.index.values.unique()
# all_feat = features.join(emd, how='inner')
all_feat = features.join(emd)
X1 = features.values.astype(np.float)
X1 = scaler.fit_transform(X1)
X2 = all_feat.values.astype(np.float)
X2 = scaler.fit_transform(X2)
names = np.array([['L2 without emd', 'L1 without emd', 'RF without emd'],
['L2 with emd', 'L1 with emd', 'RF with emd'],
['L2 just emd', 'L1 just emd', 'RF just emd']])
# names = np.array([['without MF'], ['with MF']])
n_folds = 10
results = run_all_datasets([X1, X2, emd.values], y, names, classifiers,
n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
print 'macro', results[0]
print 'micro', results[1]
macro_path = '../../results/neural/gensim_1in10000' + utils.get_timestamp(
) + '.csv'
micro_path = '../../results/neural/gensim_1in10000' + utils.get_timestamp(
) + '.csv'
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
def run_scenario(folder, embedding_path):
y_path = '../../local_resources/{}/y.p'.format(folder)
x_path = '../../local_resources/{}/X.p'.format(folder)
sizes = [2, 4, 8, 16, 32, 64, 128]
deepwalk_embeddings = []
deepwalk_names = []
dwpath = '../../local_resources/{0}/{1}'.format(folder, folder)
for size in sizes:
path = dwpath + str(size) + '.emd'
de = pd.read_csv(path, header=None, index_col=0, skiprows=1, sep=" ")
de.sort_index(inplace=True)
deepwalk_embeddings.append(de.values)
deepwalk_names.append(['deepwalk' + str(size)])
x, y = utils.read_data(x_path, y_path, threshold=0)
names = [['hyperbolic'], ['logistic']]
names = deepwalk_names + names
embedding = pd.read_csv(embedding_path, index_col=0)
X = deepwalk_embeddings + [embedding.values, normalize(x, axis=0)]
n_folds = 10
results = run_detectors.run_all_datasets(X, y, names, classifiers, n_folds)
all_results = utils.merge_results(results, n_folds)
results, tests = utils.stats_test(all_results)
tests[0].to_csv('../../results/{0}/pvalues{1}.csv'.format(
folder, utils.get_timestamp()))
tests[1].to_csv('../../results/{0}/pvalues{1}.csv'.format(
folder, utils.get_timestamp()))
print('macro', results[0])
print('micro', results[1])
macro_path = '../../results/{0}/macro{1}.csv'.format(
folder, utils.get_timestamp())
micro_path = '../../results/{0}/micro{1}.csv'.format(
folder, utils.get_timestamp())
results[0].to_csv(macro_path, index=True)
results[1].to_csv(micro_path, index=True)
