def test_warnings_raised():
if sys.version_info < (3, 4):
raise SkipTest
weights = [1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 1, 1, 2, 2, 2, 3, 3]
# faking aweights by using normalized freq_weights
weights = np.array(weights)
gid = np.arange(1, 17 + 1) // 2
cov_kwds = {'groups': gid, 'use_correction': False}
with warnings.catch_warnings(record=True) as w:
res1 = GLM(cpunish_data.endog,
cpunish_data.exog,
family=sm.families.Poisson(),
freq_weights=weights).fit(cov_type='cluster',
cov_kwds=cov_kwds)
res1.summary()
assert len(w) >= 1
with warnings.catch_warnings(record=True) as w:
res1 = GLM(cpunish_data.endog,
cpunish_data.exog,
family=sm.families.Poisson(),
var_weights=weights).fit(cov_type='cluster',
cov_kwds=cov_kwds)
res1.summary()
assert len(w) >= 1
def test_warnings_raised():
weights = [1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 1, 1, 2, 2, 2, 3, 3]
# faking aweights by using normalized freq_weights
weights = np.array(weights)
gid = np.arange(1, 17 + 1) // 2
cov_kwds = {'groups': gid, 'use_correction': False}
# Work around for buggy pytest repeated warning capture on Python 2.7
warning_type = SpecificationWarning if PY3 else None
with pytest.warns(warning_type):
res1 = GLM(cpunish_data.endog,
cpunish_data.exog,
family=sm.families.Poisson(),
freq_weights=weights).fit(cov_type='cluster',
cov_kwds=cov_kwds)
res1.summary()
with pytest.warns(warning_type):
res1 = GLM(cpunish_data.endog,
cpunish_data.exog,
family=sm.families.Poisson(),
var_weights=weights).fit(cov_type='cluster',
cov_kwds=cov_kwds)
res1.summary()
def test_warnings_raised():
weights = [1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 1, 1, 2, 2, 2, 3, 3]
# faking aweights by using normalized freq_weights
weights = np.array(weights)
gid = np.arange(1, 17 + 1) // 2
cov_kwds = {'groups': gid, 'use_correction': False}
with pytest.warns(SpecificationWarning):
res1 = GLM(cpunish_data.endog, cpunish_data.exog,
family=sm.families.Poisson(), freq_weights=weights
).fit(cov_type='cluster', cov_kwds=cov_kwds)
res1.summary()
with pytest.warns(SpecificationWarning):
res1 = GLM(cpunish_data.endog, cpunish_data.exog,
family=sm.families.Poisson(), var_weights=weights
).fit(cov_type='cluster', cov_kwds=cov_kwds)
res1.summary()
def test_warnings_raised():
weights = [1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 1, 1, 2, 2, 2, 3, 3]
# faking aweights by using normalized freq_weights
weights = np.array(weights)
gid = np.arange(1, 17 + 1) // 2
cov_kwds = {'groups': gid, 'use_correction': False}
# Work around for buggy pytest repeated warning capture on Python 2.7
warning_type = SpecificationWarning if PY3 else None
with pytest.warns(warning_type):
res1 = GLM(cpunish_data.endog, cpunish_data.exog,
family=sm.families.Poisson(), freq_weights=weights
).fit(cov_type='cluster', cov_kwds=cov_kwds)
res1.summary()
with pytest.warns(warning_type):
res1 = GLM(cpunish_data.endog, cpunish_data.exog,
family=sm.families.Poisson(), var_weights=weights
).fit(cov_type='cluster', cov_kwds=cov_kwds)
res1.summary()
def test_warnings_raised():
if sys.version_info < (3, 4):
raise SkipTest
weights = [1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 1, 1, 2, 2, 2, 3, 3]
# faking aweights by using normalized freq_weights
weights = np.array(weights)
gid = np.arange(1, 17 + 1) // 2
cov_kwds = {'groups': gid, 'use_correction': False}
with warnings.catch_warnings(record=True) as w:
res1 = GLM(cpunish_data.endog, cpunish_data.exog,
family=sm.families.Poisson(), freq_weights=weights
).fit(cov_type='cluster', cov_kwds=cov_kwds)
res1.summary()
assert len(w) >= 1
with warnings.catch_warnings(record=True) as w:
res1 = GLM(cpunish_data.endog, cpunish_data.exog,
family=sm.families.Poisson(), var_weights=weights
).fit(cov_type='cluster', cov_kwds=cov_kwds)
res1.summary()
assert len(w) >= 1
def reply_analysis_report(data_input_path, data_output_path):
reply_analysis = prepare_data_reply_analysis(data_input_path,
data_output_path)
score = reply_analysis.assign(
tweet_negative_score=lambda df: df.apply(
lambda x: x["tweet_score"]
if x["tweet_label"] == "NEGATIVE" else 1 - x["tweet_score"],
axis=1),
trump_negative_score=lambda df: df.apply(
lambda x: x["trump_score"]
if x["trump_label"] == "NEGATIVE" else 1 - x["trump_score"],
axis=1))
logits = scipy.special.logit(
score[["negative_score_retweet", "negative_score_trump"]])
logits.plot(kind="scatter",
x="negative_score_trump",
y="negative_score_retweet",
alpha=0.1)
logits.save("plots/logit_sentiment_score.png")
print(
"Naive Sentiment Score Calculation",
scipy.stats.pearsonr(logits["negative_score_trump"],
logits["negative_score_retweet"]))
tmp_data = reply_analysis[~reply_analysis["trump_label"].isnull()]
x = sm.add_constant(tmp_data[[
# "created_at_trump_day", "created_at_trump_month", "created_at_trump_year",
"followers_count_norm",
"friends_count_norm",
"listed_count_norm",
"statuses_count_norm"
]])
res = GLM(tmp_data['trump_label'].astype("category").cat.codes,
x,
family=families.Binomial()).fit(attach_wls=True, atol=1e-10)
print(res.summary())
print(
"ATE",
backdoor_binary_respose_ate(reply_analysis, "trump_label", "NEGATIVE",
"tweet_label", "NEGATIVE",
"trump_created_at", "tweet_created_at",
datetime.timedelta(minutes=0), "1D"))
import statsmodels.stats.tests.test_influence
test_module = statsmodels.stats.tests.test_influence.__file__
cur_dir = cur_dir = os.path.abspath(os.path.dirname(test_module))
file_name = "binary_constrict.csv"
file_path = os.path.join(cur_dir, "results", file_name)
df = pd.read_csv(file_path, index_col=0)
res = GLM(
df["constrict"],
df[["const", "log_rate", "log_volumne"]],
family=families.Binomial(),
).fit(attach_wls=True, atol=1e-10)
print(res.summary())
# ## get the influence measures
#
# GLMResults has a `get_influence` method similar to OLSResults, that
# returns and instance of the GLMInfluence class. This class has methods and
# (cached) attributes to inspect influence and outlier measures.
#
# This measures are based on a one-step approximation to the the results
# for deleting one observation. One-step approximations are usually accurate
# for small changes but underestimate the magnitude of large changes. Event
# though large changes are underestimated, they still show clearly the
# effect of influential observations
#
# In this example observation 4 and 18 have a large standardized residual
# and large Cook's distance, but not a large leverage. Observation 13 has
from statsmodels.genmod import families
import statsmodels.stats.tests.test_influence
test_module = statsmodels.stats.tests.test_influence.__file__
cur_dir = cur_dir = os.path.abspath(os.path.dirname(test_module))
file_name = 'binary_constrict.csv'
file_path = os.path.join(cur_dir, 'results', file_name)
df = pd.read_csv(file_path, index_col=0)
res = GLM(
df['constrict'],
df[['const', 'log_rate', 'log_volumne']],
family=families.Binomial()).fit(
attach_wls=True, atol=1e-10)
print(res.summary())
# ## get the influence measures
#
# GLMResults has a `get_influence` method similar to OLSResults, that
# returns and instance of the GLMInfluence class. This class has methods and
# (cached) attributes to inspect influence and outlier measures.
#
# This measures are based on a one-step approximation to the the results
# for deleting one observation. One-step approximations are usually accurate
# for small changes but underestimate the magnitude of large changes. Event
# though large changes are underestimated, they still show clearly the
# effect of influential observations
#
# In this example observation 4 and 18 have a large standardized residual
# and large Cook's distance, but not a large leverage. Observation 13 has
