def test_remove_empty():
cosmic = pd.read_csv(StringIO('Accession Number\tchrom\tstart\tend\n'
'ENST297338\t8\t117869609\t117869609\n'
'ENST440973\t6\t152129237\t152129237\n'
'ENST440974\t6\t152129237\t152129238\n'
'ENST440975\t6\t152129236\t152129238\n'),
sep='\t')
with pytest.raises(ValueError) as e:
remove_empty(cosmic)
assert 'No matches to write' in str(e)
cosmic = pd.read_csv(StringIO(
'Accession Number\tchrom\tstart\tend\ttest\ttest2\n'
'ENST297338\t8\t117869609\t117869609\t1\t1\n'
'ENST440973\t6\t152129237\t152129237\t0\t1\n'
'ENST440974\t6\t152129237\t152129238\t0\t2\n'
'ENST440975\t6\t152129236\t152129238\t0\t3\n'),
sep='\t')
afe(cosmic, remove_empty(cosmic))
cosmic = pd.read_csv(StringIO(
'Accession Number\tchrom\tstart\tend\ttest\ttest2\n'
'ENST297338\t8\t117869609\t117869609\t1\t1\n'
'ENST440973\t6\t152129237\t152129237\t0\t0\n'
'ENST440974\t6\t152129237\t152129238\t0\t2\n'
'ENST440975\t6\t152129236\t152129238\t0\t0\n'),
sep='\t')
expected = pd.read_csv(StringIO(
'Accession Number\tchrom\tstart\tend\ttest\ttest2\n'
'ENST297338\t8\t117869609\t117869609\t1\t1\n'
'ENST440974\t6\t152129237\t152129238\t0\t2\n'),
sep='\t')
aae(expected.values, remove_empty(cosmic).values)
def test_process_model_stats_model():
par_df = pd.DataFrame(
columns=["value", "pvalue", "standard_error", "ci_lower", "ci_upper"],
index=["const", "Age", "Sex", "BMI", "ABP"],
)
par_df["value"] = [152.133484, 37.241211, -106.577520, 787.179313, 416.673772]
par_df["pvalue"] = [
2.048808e-193,
5.616557e-01,
8.695658e-02,
5.345260e-29,
4.245663e-09,
]
par_df["standard_error"] = [2.852749, 64.117433, 62.125062, 65.424126, 69.494666]
par_df["ci_lower"] = [146.526671, -88.775663, -228.678572, 658.594255, 280.088446]
par_df["ci_upper"] = [157.740298, 163.258084, 15.523532, 915.764371, 553.259097]
info_dict = {}
info_dict["rsquared"] = 0.40026108237714
info_dict["rsquared_adj"] = 0.39477148130050055
info_dict["fvalue"] = 72.91259907398705
info_dict["f_pvalue"] = 2.700722880950139e-47
info_dict["df_model"] = 4.0
info_dict["df_resid"] = 437.0
info_dict["dependent_variable"] = "target"
info_dict["resid_std_err"] = 59.97560860753488
info_dict["n_obs"] = 442.0
res = _process_model(est)
afe(res.params, par_df)
ase(pd.Series(res.info), pd.Series(info_dict))
def test_process_frame_indices_index():
df = pd.DataFrame(np.ones((3, 3)), columns=["", "", ""])
df.index = pd.MultiIndex.from_arrays(
np.array([["today", "today", "today"], ["var1", "var2", "var3"]]))
df.index.names = ["l1", "l2"]
par_name_map = {"today": "tomorrow", "var1": "1stvar"}
index_name_map = ["period", "variable"]
column_names = list("abc")
res = _process_frame_indices(
df,
custom_param_names=par_name_map,
custom_index_names=index_name_map,
column_names=column_names,
show_col_names=True,
show_col_groups=False,
column_groups=None,
)
# expected:
params = """
period,variable,a,b,c
tomorrow,1stvar,1,1,1
tomorrow,var2,1,1,1
tomorrow,var3,1,1,1
"""
exp = _read_csv_string(params).fillna("")
exp.set_index(["period", "variable"], inplace=True)
afe(res, exp, check_dtype=False)
def test_set_params_defaults_if_missing_minimal_params(minimal_params):
user_input = minimal_params
expected = user_input.copy()
expected["lower"] = -np.inf
expected["upper"] = np.inf
expected["group"] = "All Parameters"
expected["name"] = [str(x) for x in expected.index]
res = tp._set_params_defaults_if_missing(user_input)
afe(res, expected)
def test_pdagg(self):
dfe = (self.df.groupby([pd.Grouper(key='time', freq='D')])
.agg({'duration': ['count']}).reset_index())
dfe.columns = ['time', 'duration_count']
afe(logviewer.pdagg(
self.df,
[{'key': 'time', 'freq': 'D'}],
{'duration': ['count']}),
dfe
)
def test_apply_number_format_callable():
def nsf(num, n=3):
"""n-Significant Figures"""
numstr = ("{0:.%ie}" % (n - 1)).format(num)
return numstr
raw = pd.DataFrame(data=[1234.2332, 0.0001])
exp = pd.DataFrame(data=["1.23e+03", "1.00e-04"])
res = _apply_number_format(df=raw, number_format=nsf)
afe(exp, res)
def test_set_params_defaults_if_missing_partial_params(incomplete_params):
res = tp._set_params_defaults_if_missing(incomplete_params)
expected = pd.DataFrame()
expected["value"] = [1, 2.5, 9]
expected["upper"] = [3, np.inf, np.inf]
expected["lower"] = [-np.inf, 2, 8]
expected["group"] = ["coeff", None, None]
expected["name"] = ["educ", "cutoff1", None]
afe(res, expected)
def test_process_model_dict():
df = pd.DataFrame(columns=["value", "pvalue", "standard_error"])
df["value"] = np.arange(10)
df["pvalue"] = np.arange(10)
df["standard_error"] = np.arange(10)
info = {"stat1": 0, "stat2": 0}
mod = {}
mod["params"] = df
mod["info"] = info
res = _process_model(mod)
afe(res.params, mod["params"])
ase(pd.Series(res.info), pd.Series(mod["info"]))
def test_bootstrap_from_outcomes(setup, expected):
results = bootstrap_from_outcomes(
data=setup["df"],
outcome=g,
bootstrap_outcomes=setup["estimates"],
ci_method="percentile",
)["summary"]
# use rounding to adjust precision because there is no other way of handling this
# such that it is compatible across all supported pandas versions.
afe(results.round(2), expected["results"].round(2))
def test_process_model_namedtuple():
# checks that process_model doesn't alter values
df = pd.DataFrame(columns=["value", "pvalue", "ci_lower", "ci_upper"])
df["value"] = np.arange(10)
df["pvalue"] = np.arange(10)
df["ci_lower"] = np.arange(10)
df["ci_upper"] = np.arange(10)
info = {"stat1": 0, "stat2": 0}
model = NamedTup(params=df, info=info)
res = _process_model(model)
afe(res.params, df)
ase(pd.Series(res.info), pd.Series(info))
def test_evaluate_criterion_array(minimal_params):
def return_array(params, useless_arg):
return params["value"].to_numpy()
expanded_crit = expand_criterion_output(return_array)
crit_kwargs = {"useless_arg": "hello world"}
expected_fitness_eval = 13.66666666666666666666666
expected_comparison_plot_data = minimal_params
res_fitness, res_cp_data, _ = tp._evaluate_criterion(
expanded_crit, minimal_params, crit_kwargs)
assert res_fitness == expected_fitness_eval
afe(res_cp_data, expected_comparison_plot_data)
def test_evaluate_criterion_scalar(minimal_params):
def crit_func(params, useless_arg):
return params["value"].mean()
expanded_crit = expand_criterion_output(crit_func)
crit_kwargs = {"useless_arg": "hello world"}
expected_fitness_eval = 3
expected_comparison_plot_data = pd.DataFrame()
expected_comparison_plot_data["value"] = [np.nan]
res_fitness, res_cp_data, _ = tp._evaluate_criterion(
expanded_crit, minimal_params, crit_kwargs)
assert res_fitness == expected_fitness_eval
afe(res_cp_data, expected_comparison_plot_data)
def test_process_params_df_columns():
df = pd.DataFrame(np.ones((3, 6)), columns=list("abcdef"))
custom_col_names = ["c" + str(i) for i in range(1, 7)]
custom_model_names = {"m3-5": [2, 3, 4]}
exp = _process_body_df(df, None, None, True, custom_col_names,
custom_model_names)
df.columns = pd.MultiIndex.from_arrays(
np.array([
["{}", "{}", "{m3-5}", "{m3-5}", "{m3-5}", "{}"],
["{c1}", "{c2}", "{c3}", "{c4}", "{c5}", "{c6}"],
]))
afe(df, exp, check_dtype=False)
def test_process_frame_indices_columns():
df = pd.DataFrame(np.ones((3, 3)), columns=["", "", ""])
col_names = list("abc")
col_groups = ["first", "first", "second"]
res = _process_frame_indices(
df=df,
custom_index_names=None,
custom_param_names=None,
show_col_groups=True,
show_col_names=True,
column_names=col_names,
column_groups=col_groups,
)
arrays = [np.array(col_groups), np.array(col_names)]
exp = pd.DataFrame(data=np.ones((3, 3)), columns=arrays)
afe(res, exp, check_dtype=False)
def test_filter_by_match():
infile = (
'chrom\twinstart\twinend\tn_region_ind_snps\tind_id\tpop'
'\ts_star\tnum_s_star_snps\tn_s_star_snps_hap1\tn_s_star_snps_hap2\n'
'363104291\t0\t50000\t179\tmsp_110\tEUR\t85315\t10\t2\t8\n'
'363104291\t0\t50000\t173\tmsp_111\tEUR\t47145\t4\t2\t2\n'
'363104291\t0\t50000\t174\tmsp_112\tASN\t22028\t4\t2\t2\n'
'363104291\t0\t50000\t180\tmsp_113\tEUR\t82882\t12\t7\t4\n'
'363104291\t0\t50000\t184\tmsp_114\tEUR\t111004\t15\t8\t7\n'
'363104291\t0\t50000\t174\tmsp_116\tEUR\t50976\t5\t4\t1\n'
'363104291\t0\t50000\t176\tmsp_117\tASN\t70315\t7\t7\t0\n'
'363104292\t0\t50000\t175\tmsp_118\tEUR\t67973\t3\t0\t3\n'
'363104291\t0\t50000\t171\tmsp_115\tASN\t0\t0\t0\t0\n')
window = Sstar_ECDF.process_windowcalc(StringIO(infile), 0.5)
match_file = (
'chr\tstart\tend\tisc\thaplotype\tpopulation'
'\tmatch_pct\tpvalue\tmatching_windows\n'
'363104291\t0\t50000\t199\tmsp_110:1\tEUR\t0.8\t0.01\t2217\n'
'363104291\t0\t50000\t199\tmsp_110:2\tEUR\t0.8\t0.02\t2217\n')
result = Sstar_ECDF.filter_by_match(window, StringIO(match_file), 0.02)
afe(
result,
pd.DataFrame({
'start': [0],
'end': [50000],
'n_region_ind_snps': [179],
'pop': ['EUR'],
's_star': [85315],
'msp_ID': ['msp_110:2_363104291'],
}))
# result empty as pvalue too low
result = Sstar_ECDF.filter_by_match(window, StringIO(match_file), 0.01)
afe(result,
pd.DataFrame({
'start': [],
'end': [],
'n_region_ind_snps': [],
'pop': [],
's_star': [],
'msp_ID': [],
}),
check_index_type=False,
check_dtype=False)
def test_estimation_table():
models = [est]
return_type = "python"
res = estimation_table(models, return_type, append_notes=False)
exp = {}
body_str = """
index,{(1)}
const,152.13$^{*** }$
,(2.85)
Age,37.24$^{ }$
,(64.12)
Sex,-106.58$^{* }$
,(62.13)
BMI,787.18$^{*** }$
,(65.42)
ABP,416.67$^{*** }$
,(69.49)
"""
exp["body_df"] = _read_csv_string(body_str).fillna("")
exp["body_df"].set_index("index", inplace=True)
footer_str = """
,{(1)}
Observations,442.0
R$^2$,0.4
Adj. R$^2$,0.39
Residual Std. Error,59.98
F Statistic,72.91$^{***}$
"""
exp["footer_df"] = _read_csv_string(footer_str).fillna("")
exp["footer_df"].set_index(" ", inplace=True)
exp["footer_df"].index.names = [None]
exp["footer_df"].index = pd.MultiIndex.from_arrays([exp["footer_df"].index])
exp["notes_tex"] = "\\midrule\n"
exp[
"notes_html"
] = """<tr><td colspan="2" style="border-bottom: 1px solid black">
</td></tr>"""
afe(exp["footer_df"], res["footer_df"])
afe(exp["body_df"], res["body_df"], check_index_type=False)
ase(pd.Series(exp["notes_html"]), pd.Series(res["notes_html"]))
ase(pd.Series(exp["notes_tex"]), pd.Series(res["notes_tex"]))
def test_get_params_frames_with_common_index():
m1 = {
"params": pd.DataFrame(np.ones(5), index=list("abcde")),
"info": None,
"name": None,
}
m2 = {
"params": pd.DataFrame(np.ones(3), index=list("abc")),
"info": None,
"name": None,
}
res = _get_params_frames_with_common_index([m1, m2])
exp = [
pd.DataFrame(np.ones(5), index=list("abcde")),
pd.DataFrame(np.concatenate([np.ones(3),
np.ones(2) * np.nan]),
index=list("abcde")),
]
afe(res[0], exp[0])
afe(res[1], exp[1])
def test_read_pon():
vcf = StringIO(
'##tumor_sample=P9-C3\n'
'#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n'
'1\t10146\t.\tAC\tA\t.\t.\t.\n'
'1\t10151\t.\tTA\tT,GA\t.\t.\t.\n'
'1\t10403\t.\tACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAAC\tA\t.\t.\t.\n'
'1\t10415\t.\tACCCTAACCCTAACCCTAACCCTAAC\tA\t.\t.\t.\n'
'hs37d5\t35466424\t.\tG\tGATTCC\t.\t.\t.\n'
'hs37d5\t35466456\t.\tC\tT\t.\t.\t.\n'
'X\t155260422\t.\tAGGGGTTAGGGGTTAG\tAGGGTTAGGGGTTAG,A\t.\t.\t.\n'
'Y\t2661694\t.\tA\tG\t.\t.\t.\n'
'MT\t151\t.\tCT\tTT,TC\t.\t.\t.')
result = read_pon(vcf)
expected = pd.read_csv(StringIO('chrom\tpos\n'
'1\t10146\n'
'1\t10151\n'
'1\t10403\n'
'1\t10415\n'),
sep='\t')
afe(result, expected)
def test_get_params_frames_with_common_index_multiindex():
mi = pd.MultiIndex.from_tuples([("a", 1), ("a", 2), ("b", 1), ("b", 2),
("b", 3)])
m1 = {
"params": pd.DataFrame(np.ones(5), index=mi),
"info": None,
"name": None
}
m2 = {
"params": pd.DataFrame(np.ones(3), index=mi[:3]),
"info": None,
"name": None
}
res = _get_params_frames_with_common_index([m1, m2])
exp = [
pd.DataFrame(np.ones(5), index=mi),
pd.DataFrame(np.concatenate([np.ones(3),
np.ones(2) * np.nan]),
index=mi),
]
afe(res[0], exp[0])
afe(res[1], exp[1])
def test_estimation_table():
models = [est]
res = estimation_table(models,
return_type="render_inputs",
append_notes=False)
exp = {}
body = """
index,target
const,152.00$^{*** }$
,(2.85)
Age,37.20$^{ }$
,(64.10)
Sex,-107.00$^{* }$
,(62.10)
BMI,787.00$^{*** }$
,(65.40)
ABP,417.00$^{*** }$
,(69.50)
"""
exp["body"] = _read_csv_string(body).fillna("")
exp["body"].set_index("index", inplace=True)
footer_str = """
,target
R$^2$,0.40
Adj. R$^2$,0.40
Residual Std. Error,60
F Statistic,72.90$^{***}$
Observations,442
"""
exp["footer"] = _read_csv_string(footer_str).fillna("")
exp["footer"].set_index(" ", inplace=True)
exp["footer"].index.names = [None]
exp["footer"].index = pd.MultiIndex.from_arrays([exp["footer"].index])
afe(exp["footer"].sort_index(), res["footer"].sort_index())
afe(exp["body"], res["body"], check_index_type=False)
def test_tabulate_pon():
cosmic = pd.read_csv(StringIO('Accession Number\tchrom\tstart\tend\n'
'ENST297338\t8\t117869609\t117869609\n'
'ENST440973\t6\t152129237\t152129237\n'
'ENST440974\t6\t152129237\t152129238\n'
'ENST440975\t6\t152129236\t152129238\n'),
sep='\t')
pon = pd.read_csv(StringIO('chrom\tpos\n'
'1\t10151\n'
'1\t10403\n'
'1\t10415\n'),
sep='\t')
result = tabulate_pon(cosmic, pon, 'test')
afe(result, cosmic)
pon = pd.read_csv(StringIO('chrom\tpos\n'
'8\t117869609\n'
'1\t10403\n'
'1\t10415\n'),
sep='\t')
cosmic = tabulate_pon(cosmic, pon, 'test')
expected = pd.read_csv(StringIO(
'Accession Number\tchrom\tstart\tend\ttest\n'
'ENST297338\t8\t117869609\t117869609\t1\n'
'ENST440973\t6\t152129237\t152129237\t0\n'
'ENST440974\t6\t152129237\t152129238\t0\n'
'ENST440975\t6\t152129236\t152129238\t0\n'),
sep='\t')
afe(cosmic, expected)
pon = pd.read_csv(StringIO('chrom\tpos\n'
'8\t117869609\n'
'6\t152129235\n'
'6\t152129236\n'
'6\t152129237\n'
'6\t152129238\n'
'6\t152129239\n'),
sep='\t')
cosmic = tabulate_pon(cosmic, pon, 'test2')
expected = pd.read_csv(StringIO(
'Accession Number\tchrom\tstart\tend\ttest\ttest2\n'
'ENST297338\t8\t117869609\t117869609\t1\t1\n'
'ENST440973\t6\t152129237\t152129237\t0\t1\n'
'ENST440974\t6\t152129237\t152129238\t0\t2\n'
'ENST440975\t6\t152129236\t152129238\t0\t3\n'),
sep='\t')
afe(cosmic, expected)
def test_get_bootstrap_samples_from_indices():
indices = [np.array([0, 1])]
data = pd.DataFrame(np.arange(6).reshape(3, 2))
expected = pd.DataFrame(np.arange(4).reshape(2, 2))
calculated = _get_bootstrap_samples_from_indices(data, indices)[0]
afe(calculated, expected)
def test_filter_by_sstar():
df = pd.DataFrame({
'start': [0, 0, 0],
'end': [50000, 50000, 50000],
'n_region_ind_snps': [179, 179, 178],
'pop': ['EUR', 'EUR', 'EUR'],
's_star': [85315, 85314, 85313],
'msp_ID':
['msp_110:2_363104292', 'msp_110:2_363104293', 'msp_110:2_363104291'],
})
null_db = Sstar_ECDF.Null_DB()
index = pd.MultiIndex.from_tuples(
[
('EUR', 179, 25211),
('EUR', 179, 85313),
('EUR', 179, 85314),
('EUR', 179, 85315),
('EUR', 179, 85316),
('EUR', 178, 25211),
],
names=['pop', 'n_region_ind_snps', 's_star'])
null_db.DB = pd.Series([2, 2, 2, 2, 2, 2], index=index)
# nothing
result = Sstar_ECDF.filter_by_sstar(df, null_db, -1)
afe(result,
pd.DataFrame({
'start': [],
'end': [],
'msp_ID': []
}),
check_like=True,
check_dtype=False)
# last
result = Sstar_ECDF.filter_by_sstar(df, null_db, 0)
afe(result,
pd.DataFrame({
'start': [0],
'end': [50000],
'msp_ID': ['msp_110:2_363104291']
}),
check_like=True,
check_dtype=False)
result = Sstar_ECDF.filter_by_sstar(df, null_db, 0.2)
afe(result,
pd.DataFrame({
'start': [0, 0],
'end': [50000, 50000],
'msp_ID': ['msp_110:2_363104291', 'msp_110:2_363104292']
}),
check_like=True,
check_dtype=False)
# Note, groupby sorts by pop, then n_region
result = Sstar_ECDF.filter_by_sstar(df, null_db, 0.4)
afe(result,
pd.DataFrame({
'start': [0, 0, 0],
'end': [50000, 50000, 50000],
'msp_ID': [
'msp_110:2_363104291', 'msp_110:2_363104292',
'msp_110:2_363104293'
]
}),
check_like=True,
check_dtype=False)
# empty window input
df = pd.DataFrame({
'start': [],
'end': [],
'n_region_ind_snps': [],
'pop': [],
's_star': [],
'msp_ID': [],
})
result = Sstar_ECDF.filter_by_sstar(df, null_db, 0.05)
afe(result,
pd.DataFrame({
'start': [],
'end': [],
'msp_ID': []
}),
check_like=True,
check_dtype=False)
def test_endpoints(self):
self.check('/logviewer/')
self.check('/logviewer/query/', code=404)
# check query endpoints
spec = self.get_keywith(conf.url, 'apps/logviewer/query-')
base = '/logviewer/query/aggD'
df = self.df
df_user1 = df['user.id_1'].eq(1)
df_uri1 = df['uri_1'].eq(1)
# check filters
for col in ['status', 'ip']:
eq_(
self.get('{}/filter{}/'.format(base, col)).json(), [{
col: x
} for x in sorted(df[col].unique().astype(str))])
eq_(
self.get('{}/filter{}/?_limit=10000'.format(base, 'users')).json(),
[{
'user.id': x
} for x in sorted(df[df_user1]['user.id'].unique())])
# ToDo: See https://github.com/gramener/gramex/issues/252
ideal = df[df_uri1]['uri'].value_counts().astype(int)[:100]
ideal = ideal.rename_axis('uri').reset_index(name='views')
ideal = ideal.sort_values(by=['views', 'uri'], ascending=[False, True])
ideal.reset_index(inplace=True, drop=True)
actual = self.get('{}/filter{}/'.format(base, 'uri')).json()
actual = pd.DataFrame.from_records(actual)
actual.sort_values(by=['views', 'uri'],
ascending=[False, True],
inplace=True)
actual.reset_index(inplace=True, drop=True)
afe(actual, ideal)
# check KPIs
eq_(
self.get('{}/kpi-{}/'.format(base, 'pageviews')).json(),
[{
'value': len(df[df_uri1].index)
}])
eq_(
self.get('{}/kpi-{}/'.format(base, 'sessions')).json(),
[{
'value': df[df_user1]['new_session'].sum()
}])
eq_(
self.get('{}/kpi-{}/'.format(base, 'users')).json(),
[{
'value': df[df_user1]['user.id'].nunique()
}])
eq_(
self.get('{}/kpi-{}/'.format(base, 'urls')).json(),
[{
'value': df[df_uri1]['uri'].nunique()
}])
r = self.get('{}/kpi-{}/'.format(base, 'avgtimespent')).json()
aae(
r[0]['value'], df[df_user1]['session_time'].sum() /
df[df_user1]['new_session'].sum(), 4)
r = self.get('{}/kpi-{}/'.format(base, 'avgloadtime')).json()
aae(r[0]['value'], df['duration'].mean(), 4)
# check top10
topten = [{
'col': 'user.id',
'url': 'users',
'values': 'views',
'flag': True
}, {
'col': 'ip',
'url': 'ip',
'values': 'requests'
}, {
'col': 'status',
'url': 'status',
'values': 'requests'
}, {
'col': 'uri',
'url': 'uri',
'values': 'views',
'flag': True
}]
for top in topten:
cond = (df[top['col'] +
'_1'].eq(1) if top.get('flag') else slice(None))
eq_(
self.get('{}/topten{}/'.format(base, top['url'])).json(),
(df[cond][top['col']].value_counts().astype(int).rename_axis(
top['col']).reset_index(name=top['values']).sort_values(
by=[top['values'], top['col']],
ascending=[False, True])[:10].to_dict('r')))
# check trend
dff = logviewer.pdagg(df[df_uri1], [{
'key': 'time',
'freq': 'D'
}], {'duration': ['count']})
dff['time'] = dff['time'].dt.strftime('%Y-%m-%d 00:00:00')
dff['pageviews'] = dff['duration_count'].astype(int)
dff = dff[dff['pageviews'].ne(0)]
eq_(
self.get('{}/{}/'.format(base, 'pageviewstrend')).json(),
dff.drop('duration_count', 1).to_dict('r'))
dff = logviewer.pdagg(df[df_user1], [{
'key': 'time',
'freq': 'D'
}], {'new_session': ['sum']})
dff['time'] = dff['time'].dt.strftime('%Y-%m-%d 00:00:00')
dff['sessions'] = dff['new_session_sum'].astype(int)
dff = dff[dff['sessions'].ne(0)]
eq_(
self.get('{}/{}/'.format(base, 'sessionstrend')).json(),
dff.drop('new_session_sum', 1).query('sessions != 0').to_dict('r'))
# TODO trend queries
for q in spec.kwargs.kwargs.queries.keys():
if q.endswith('trend'):
self.check('{}/{}/'.format(base, q))
def test_apply_number_format_int():
number_format = 3
raw = pd.DataFrame(data=["1234.2332", "1.2e+03"])
exp = pd.DataFrame(data=["1234.233", "1.2e+03"])
res = _apply_number_format(df=raw, number_format=number_format)
afe(exp, res)
def test_apply_number_format_tuple():
number_format = ("{0:.2g}", "{0:.2f}", "{0:.2g}")
raw = pd.DataFrame(data=[1234.2332, 0.0001])
exp = pd.DataFrame(data=["1.2e+03", "0"])
res = _apply_number_format(df=raw, number_format=number_format)
afe(exp, res)
