def income_different_size_embedding_scenario():
# names = np.array(
# [['ridge without emd', 'RF without emd'],
# ['ridge with emd', 'RF with emd'],
# ['ridge just emd', 'RF just emd']])
# names = [['ridge', 'RF']]
names = [['ridge']]
y_path = '../local_resources/Socio_economic_classification_data/income_dataset/y_thresh10.p'
target = utils.read_target(y_path)
y = np.array(target['mean_income'])
n_folds = 10
sizes = [16, 32, 64, 128]
for size in sizes:
print 'running embeddings of size ', size
emd_path = '../local_resources/Socio_economic_classification_data/income_dataset/thresh10_{0}.emd'.format(
size)
x = utils.read_embedding(emd_path, target)
results = run_all_datasets([x], y, names, regressors, n_folds)
# all_results = utils.merge_results(results)
all_results = pd.concat([x for x in results])
all_results.rename(columns={n_folds: 'train'}, inplace=True)
results, tests = t_tests(all_results)
print results
path = '../results/income/thresh10_' + str(
size) + '_' + utils.get_timestamp() + '.csv'
results.to_csv(path, index=True)
def karate_test_scenario(deepwalk_path):
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 = [['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 tsne_plot():
model = TSNE(n_components=2, random_state=0)
x_path = '../../local_resources/income_dataset/X_thresh10.p'
y_path = '../../local_resources/income_dataset/y_thresh10.p'
emd_path = '../../local_results/dimension_32_num_10_length_80_context_10.emd'
outpath = '../../local_results/figures/tsne.pdf'
X, y = utils.read_data(x_path, y_path, threshold=10)
target = utils.read_target(y_path)
emd = pd.read_csv(emd_path, header=None, index_col=0, skiprows=1, sep=",")
embedding = model.fit_transform(emd)
# sb.set_context("notebook", font_scale=1.1)
sns.set_style("ticks")
print 'embedding shape is ', embedding.shape
df = pd.DataFrame(data=embedding, index=None, columns=['x', 'y'])
labels = np.array(target.loc[emd.index].mean_income)
df['label'] = labels
df.to_csv('../../local_results/tsne.csv', index=None)
plot = sns.lmplot('x',
'y',
data=df,
fit_reg=False,
hue="label",
scatter_kws={
"marker": "D",
"s": 10
})
plot.savefig(outpath)
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 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 scenario_vary_walks_and_context():
print 'reading data'
x, y = utils.read_data('../../local_resources/income_dataset/X_thresh10.p',
'../../local_resources/income_dataset/y_thresh10.p', 0)
n_vertices = len(y)
s = datetime.now()
g = BipartiteGraph(x)
# print 'building edges'
# g.build_edge_array()
all_walks = pd.read_csv('../../local_results/thresh10_walks_length_100_num_walks_20.csv',
header=None).values
target = utils.read_target('../../local_resources/income_dataset/y_thresh10.p')
num_walks = [6, 8, 10, 12, 14, 16, 18, 20]
print 'running number of walks loop'
for n_walks in num_walks:
walks = all_walks[0:n_walks * n_vertices, 0:80]
print 'walk shape is ', walks.shape
outpath = '../../local_results/dimension_32_num_{}_length_10_context_10.emd'.format(n_walks)
np.random.shuffle(walks)
g.learn_embeddings(walks, size=32, outpath=outpath, window_size=10)
change_index(outpath, target)
print 'number of walks ', str(n_walks), ' embeddings generated in ', datetime.now() - s, ' s'
walk_lengths = [40, 50, 60, 70, 80, 90, 100]
print 'running walk length loop'
for walk_length in walk_lengths:
walks = all_walks[0:10 * n_vertices, 0:walk_length]
print 'walk shape is ', walks.shape
outpath = '../../local_results/dimension_32_num_10_length_{}_context_10.emd'.format(walk_length)
np.random.shuffle(walks)
g.learn_embeddings(walks, size=32, outpath=outpath, window_size=10)
change_index(outpath, target)
print 'length ', str(walk_length), ' embeddings generated in ', datetime.now() - s, ' s'
context_size = [8, 10, 12, 14, 16, 18, 20]
print 'running context size loop'
for size in context_size:
walks = all_walks[0:10 * n_vertices, 0:80]
print 'walk shape is ', walks.shape
outpath = '../../local_results/dimension_32_num_10_length_80_context_{}.emd'.format(size)
np.random.shuffle(walks)
g.learn_embeddings(walks, size=32, outpath=outpath, window_size=size)
change_index(outpath, target)
print 'context size ', str(size), ' embeddings generated in ', datetime.now() - s, ' s'
def nikos_test_scenario():
names = [['ridge']]
y_path = '../local_resources/Socio_economic_classification_data/income_dataset/y_thresh10.p'
target = utils.read_target(y_path)
y = np.array(target['mean_income'])
n_folds = 10
sizes = [16, 32, 64, 128]
for size in sizes:
print 'running for size {} \n'.format(size)
emd_path = '../local_resources/Socio_economic_classification_data/income_dataset/thresh10_{0}.emd'.format(
size)
x = pd.read_csv(emd_path, index_col=0)
x = x.as_matrix()
results = run_all_datasets([x], y, names, regressors, n_folds)
all_results = pd.concat([x for x in results])
all_results.rename(columns={n_folds: 'train'}, inplace=True)
results, tests = t_tests(all_results)
print results
def reindex_embeddings():
"""
changes the first column of embeddings from an index to a Twitter ID
:return:
"""
y_path = '../../local_resources/income_dataset/y_thresh10.p'
target = utils.read_target(y_path)
sizes = [16, 32, 64, 128]
for size in sizes:
print 'running embeddings of size ', size
emd_path = '../../local_results/income_dataset/thresh10_{0}.emd'.format(
size)
x = utils.read_embedding(emd_path, target)
df = pd.DataFrame(data=x, index=target.index)
try:
del df.index.name
except AttributeError:
pass
df.to_csv(emd_path)
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 income_scenario():
# names = np.array(
# [['ridge without emd', 'RF without emd'],
# ['ridge with emd', 'RF with emd'],
# ['ridge just emd', 'RF just emd']])
# names = [['ridge', 'RF']]
names = [['ridge']]
y_path = '../local_resources/Socio_economic_classification_data/income_dataset/y_thresh10.p'
emd_path = '../local_resources/Socio_economic_classification_data/income_dataset/thresh10_64.emd'
target = utils.read_target(y_path)
x = utils.read_embedding(emd_path, target)
y = np.array(target['mean_income'])
n_folds = 10
# x, y = utils.read_data(x_path, y_path, threshold=1)
results = run_all_datasets([x], y, names, regressors, n_folds)
# all_results = utils.merge_results(results)
all_results = pd.concat([x for x in results])
all_results.rename(columns={n_folds: 'train'}, inplace=True)
results, tests = t_tests(all_results)
print results
path = '../results/income/thresh10_' + utils.get_timestamp() + '.csv'
results.to_csv(path, index=True)
df.to_csv(emd_path)
def reindex_embeddings():
"""
changes the first column of embeddings from an index to a Twitter ID
:return:
"""
y_path = '../../local_resources/income_dataset/y_thresh10.p'
target = utils.read_target(y_path)
sizes = [16, 32, 64, 128]
for size in sizes:
print 'running embeddings of size ', size
emd_path = '../../local_results/income_dataset/thresh10_{0}.emd'.format(
size)
x = utils.read_embedding(emd_path, target)
df = pd.DataFrame(data=x, index=target.index)
try:
del df.index.name
except AttributeError:
pass
df.to_csv(emd_path)
if __name__ == '__main__':
scenario_build_income_embeddings(emd_dimension=2)
target = utils.read_target('../../local_resources/income_dataset/y_thresh10.p')
change_index('../../local_results/thresh10_num_10_length_80_dimension_2.emd', target)