def test_find_truffles():
posts = create_n_random_posts(300)
post_frame = pd.DataFrame(posts)
regressor_kwargs = dict(n_estimators=20,
max_leaf_nodes=100,
max_features=0.1,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=50, no_below=5, no_above=0.7)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=50)
pipeline = tpmo.train_pipeline(post_frame,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
posts = create_n_random_posts(50)
post_frame = pd.DataFrame(posts)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=50)
truffles = tpmo.find_truffles(post_frame, pipeline, account='aa')
assert truffles.iloc[0].rank_score == truffles.rank_score.max()
def test_test_top_trending_post(steem):
if config.PASSWORD:
steem.wallet.unlock(config.PASSWORD)
poster = Poster(steem=steem,
account=config.ACCOUNT,
waiting_time=0.1,
no_posting_key_mode=config.PASSWORD is None)
posts = random_data.create_n_random_posts(10)
df = pd.DataFrame(posts)
df['reward'] = df.reward
df['predicted_votes'] = df.votes
df = tppp.preprocess(df, ncores=1)
date = pd.datetime.utcnow().date()
tbpd.post_top_trending_list(df,
poster,
date,
overview_permalink='iii',
trufflepicks_permalink='kkk',
steem_amount=10,
sbd_amount=10)
def test_crossval():
posts = create_n_random_posts(100)
post_frame = pd.DataFrame(posts)
regressor_kwargs = dict(n_estimators=20,
max_leaf_nodes=100,
max_features=0.1,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=50, no_below=5, no_above=0.7)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=20)
param_grid = {
'feature_generation__topic_model__no_above': [0.2, 0.3],
'regressor__max_leaf_nodes': [50, 100],
}
tpmo.cross_validate(post_frame,
param_grid,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
def test_statistics():
posts = create_n_random_posts(300)
post_frame = pd.DataFrame(posts)
current_date = pd.datetime.utcnow()
regressor_kwargs = dict(n_estimators=20,
max_leaf_nodes=100,
max_features=0.1,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=50, no_below=5, no_above=0.7)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=50)
pipeline = tpmo.train_pipeline(post_frame,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
post_frame['steem_bought_reward'] = 0
post_frame['sbd_bought_reward'] = 0
post_frame['bought_votes'] = 0
stats = tppw.compute_weekly_statistics(post_frame, pipeline)
steem_per_mvests = 490
delegator_list = ['peter', 'paul']
title, body = tpbp.weekly_update(steem_per_mvests=steem_per_mvests,
current_datetime=current_date,
delegator_list=delegator_list,
**stats)
assert title
assert body
def test_weekly_post(steem):
posts = create_n_random_posts(300)
post_frame = pd.DataFrame(posts)
current_date = pd.datetime.utcnow()
regressor_kwargs = dict(n_estimators=20,
max_leaf_nodes=100,
max_features=0.1,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=50, no_below=5, no_above=0.7)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=50)
pipeline = tpmo.train_pipeline(post_frame,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
post_frame['steem_bought_reward'] = 0
post_frame['sbd_bought_reward'] = 0
post_frame['bought_votes'] = 0
poster = Poster(account=config.ACCOUNT,
steem=steem,
no_posting_key_mode=config.PASSWORD is None)
permalink = tppw.post_weakly_update(pipeline,
post_frame,
poster=poster,
current_datetime=current_date)
assert permalink
def test_comment():
post = random_data.create_n_random_posts(1)[0]
result = tbpo.truffle_comment(reward=post['reward'],
votes=post['votes'],
rank=1,
topN_link='www.example.com',
truffle_link='www.tf.tf')
assert result
def test_preprocessing_random_parallel():
posts = create_n_random_posts(50)
post_frame = pd.DataFrame(posts)
filtered = tppp.preprocess(post_frame,
ncores=5,
chunksize=10,
min_en_prob=0.5,
max_errors_per_word=0.5,
min_max_num_words=(10, 99999))
assert len(filtered) > 20
def test_store_load_frame_test(temp_dir):
filename = os.path.join(temp_dir, 'test.sqlite')
x = pd.DataFrame(create_n_random_posts(42))
x = tppp.preprocess(x)
tppe.to_sqlite(x, filename, 'test')
y = tppe.from_sqlite(filename, 'test')
pd.testing.assert_frame_equal(x,y)
def test_tag_measure():
posts = create_n_random_posts(100)
post_frame = pd.DataFrame(posts)
post_frame = tppp.preprocess(post_frame, ncores=1)
post_frame['predicted_reward'] = post_frame.reward
tag_measure = tpmo.compute_tag_factor(post_frame.tags, tpmo.PUNISH_LIST)
assert np.all(tag_measure > 0)
def test_topN_comment():
posts = random_data.create_n_random_posts(25)
df = pd.DataFrame(posts)
df = tppp.preprocess(df, ncores=1)
post = tbpo.topN_comment(topN_authors=df.author,
topN_permalinks=df.permalink,
topN_titles=df.title,
topN_votes=df.votes,
topN_rewards=df.reward)
assert post
def test_Doc2Vec_KNN():
posts = create_n_random_posts(100)
post_frame = pd.DataFrame(posts)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=30)
pipe = tpmo.create_pure_doc2vec_pipeline(dict(epochs=2, size=16))
pipe, frame = tpmo.train_test_pipeline(post_frame,
pipeline=pipe,
sample_weight_function=None)
pass
def test_train_test_pipeline():
posts = create_n_random_posts(300)
post_frame = pd.DataFrame(posts)
regressor_kwargs = dict(n_estimators=20,
max_leaf_nodes=100,
max_features=0.1,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=50, no_below=5, no_above=0.7)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=50)
tpmo.train_test_pipeline(post_frame,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
def test_load_or_preproc(temp_dir):
filename = os.path.join(temp_dir, 'pptest.gz')
post_frame = pd.DataFrame(create_n_random_posts(10))
frame = tppp.load_or_preprocess(post_frame,
filename,
ncores=5,
chunksize=20)
assert len(os.listdir(temp_dir)) == 1
frame2 = tppp.load_or_preprocess(post_frame,
filename,
ncores=5,
chunksize=20)
assert len(os.listdir(temp_dir)) == 1
assert_frame_equal(frame, frame2)
def test_topN_post():
posts = random_data.create_n_random_posts(10)
df = pd.DataFrame(posts)
df = tppp.preprocess(df, ncores=1)
date = pd.datetime.utcnow().date()
df.image_urls = df.body.apply(lambda x: tptf.get_image_urls(x))
title, post = tbpo.topN_post(topN_authors=df.author,
topN_permalinks=df.permalink,
topN_titles=df.title,
topN_filtered_bodies=df.filtered_body,
topN_image_urls=df.image_urls,
topN_rewards=df.reward,
topN_votes=df.votes,
title_date=date,
truffle_link='de.de.de')
assert post
assert title
def test_test_top20_vote_and_comment(steem):
if config.PASSWORD:
steem.wallet.unlock(config.PASSWORD)
poster = Poster(steem=steem,
account=config.ACCOUNT,
waiting_time=0.1,
no_posting_key_mode=config.PASSWORD is None)
posts = random_data.create_n_random_posts(10)
df = pd.DataFrame(posts)
df['predicted_reward'] = df.reward
df['predicted_votes'] = df.votes
df = tppp.preprocess(df, ncores=1)
tbpd.vote_and_comment_on_topK(df,
poster,
'laida',
overview_permalink='lll')
def test_bid_bot_correction():
posts = create_n_random_posts(30)
post_frame = pd.DataFrame(posts)
bought = {}
bought[('hello', 'kitty')] = ['19 STEEM']
sample_frame = post_frame[['author', 'permalink']].sample(10)
for _, (author, permalink) in sample_frame.iterrows():
bought[(author, permalink)] = {
'aaa': {
'amount': '3 STEEM'
},
'bbb': {
'amount': '4 SBD'
}
}
post_frame = tppp.compute_bidbot_correction(post_frame, bought)
assert post_frame.adjusted_reward.mean() < post_frame.reward.mean()
assert all(post_frame.adjusted_reward >= 0)
assert post_frame.adjusted_votes.mean() < post_frame.votes.mean()
assert all(post_frame.adjusted_votes >= 0)
def test_test_top10post(steem):
if config.PASSWORD:
steem.wallet.unlock(config.PASSWORD)
poster = Poster(steem=steem,
account=config.ACCOUNT,
waiting_time=0.1,
no_posting_key_mode=config.PASSWORD is None)
posts = random_data.create_n_random_posts(10)
df = pd.DataFrame(posts)
df['predicted_reward'] = df.reward
df['predicted_votes'] = df.votes
df = tppp.preprocess(df, ncores=1)
date = pd.datetime.utcnow().date()
account = config.ACCOUNT
permalink = tbpd.post_topN_list(df, poster, date, overview_permalink='iii')
tbpd.comment_on_own_top_list(df, poster, permalink)
def test_load_or_train(temp_dir):
cdt = pd.datetime.utcnow()
posts = create_n_random_posts(300)
post_frame = pd.DataFrame(posts)
regressor_kwargs = dict(n_estimators=20,
max_leaf_nodes=100,
max_features=0.1,
n_jobs=-1,
verbose=1,
random_state=42)
topic_kwargs = dict(num_topics=50, no_below=5, no_above=0.7)
post_frame = tppp.preprocess(post_frame, ncores=4, chunksize=50)
pipe = tpmo.load_or_train_pipeline(post_frame,
temp_dir,
current_datetime=cdt,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
topic_model = pipe.named_steps['feature_generation'].transformer_list[1][1]
result = topic_model.print_topics()
assert result
assert len(os.listdir(temp_dir)) == 1
pipe2 = tpmo.load_or_train_pipeline(post_frame,
temp_dir,
current_datetime=cdt,
topic_kwargs=topic_kwargs,
regressor_kwargs=regressor_kwargs)
assert len(os.listdir(temp_dir)) == 1
assert set(pipe.named_steps.keys()) == set(pipe2.named_steps.keys())
