Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

746 tests vdataframe math and rolling #776

Merged
merged 4 commits into from
Oct 31, 2023
Merged

746 tests vdataframe math and rolling #776

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
086034a
UT code for math and rolling functions
vikash018 Oct 25, 2023
f5f7a02
moved reusable code to init file
vikash018 Oct 25, 2023
7fd52ba
Merge branch 'master' into 746-tests-vdataframe-math-and-rolling
vikash018 Oct 26, 2023
bca7bf6
black format chnage for machine_learning/memmodel/naive_bayes.py
vikash018 Oct 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion verticapy/machine_learning/memmodel/naive_bayes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ class NaiveBayes(MulticlassClassifier):
'male': 0.583333333333333},
'S': {'female': 0.311212814645309,
'male': 0.688787185354691}}

prior: ArrayLike
The model's classes probabilities.
classes: ArrayLike
Expand Down
71 changes: 71 additions & 0 deletions verticapy/tests_new/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,3 +14,74 @@
See the License for the specific language governing
permissions and limitations under the License.
"""
from collections import namedtuple

AggregateFun = namedtuple("AggregateFun", ["vpy", "py"])
functions = {
"aad": [
"vpy_data.aad()",
"np.absolute(py_data - py_data.mean(numeric_only=True)).mean(numeric_only=True)",
],
"count": ["vpy_data.count()", "py_data.count()"],
"cvar": [
"vpy_data.cvar()",
"py_data[py_data >= py_data.quantile(0.95, numeric_only=True)].mean(numeric_only=True)",
],
"iqr": [
"vpy_data.iqr()",
"py_data.quantile(0.75, numeric_only=True) - py_data.quantile(0.25, numeric_only=True)",
],
"kurt": ["vpy_data.kurt()", "py_data.kurt(numeric_only=True)"],
"kurtosis": [
"vpy_data.kurtosis()",
"py_data.kurtosis(numeric_only=True)",
],
"jb": ["vpy_data.jb()", "jarque_bera(py_data, nan_policy='omit').statistic"],
"mad": [
"vpy_data.mad()",
"median_abs_deviation(py_data, nan_policy='omit')",
],
"max": ["vpy_data.max()", "py_data.max(numeric_only=True)"],
"mean": ["vpy_data.mean()", "py_data.mean(numeric_only=True)"],
"avg": ["vpy_data.avg()", "py_data.mean(numeric_only=True)"],
"median": ["vpy_data.median()", "py_data.median(numeric_only=True)"],
"min": ["vpy_data.min()", "py_data.min(numeric_only=True)"],
"mode": ["vpy_data.mode()", "py_data.mode(numeric_only=True, dropna=False).values"],
"percent": ["vpy_data.percent()", "py_data.count()/len(py_data)*100"],
"quantile": [
"vpy_data.quantile(q=[0.2, 0.5])",
"py_data.quantile(q=[0.2, 0.5],numeric_only=True).values",
],
"10%": ["vpy_data.q10()", "py_data.quantile(0.1, numeric_only=True)"],
"90%": ["vpy_data.q90", "py_data.quantile(0.9, numeric_only=True)"],
"prod": ["vpy_data.prod()", "py_data.prod(numeric_only=True)"],
"product": ["vpy_data.product()", "py_data.product(numeric_only=True)"],
"range": [
"vpy_data.range()",
"py_data.max(numeric_only=True) - py_data.min(numeric_only=True)",
],
"sem": ["vpy_data.sem()", "py_data.sem(numeric_only=True)"],
"skew": ["vpy_data.skew()", "py_data.skew(numeric_only=True)"],
"skewness": ["vpy_data.skewness()", "py_data.skew(numeric_only=True)"],
"sum": ["vpy_data.sum()", "py_data.sum(numeric_only=True)"],
"std": ["vpy_data.std()", "py_data.std(numeric_only=True)"],
"stddev": ["vpy_data.stddev()", "py_data.std(numeric_only=True)"],
"topk": ["vpy_data.topk(k=3)", "py_data.value_counts(dropna=False)"],
"top1": ["vpy_data.topk(k=1)", "py_data.value_counts(dropna=False).index[0]"],
"top1_percent": [
"vpy_data.top1_percent()",
"py_data.value_counts(dropna=False).iloc[0]/len(py_data)*100",
],
"nunique": ["vpy_data.nunique(approx=False)", "py_data.nunique()"],
"unique": ["vpy_data.nunique(approx=False)", "py_data.nunique()"],
"var": ["vpy_data.var()", "py_data.var(numeric_only=True)"],
"variance": ["vpy_data.variance()", "py_data.var(numeric_only=True)"],
"value_counts": [
"vpy_data.value_counts()",
"py_data.value_counts(dropna=False)",
],
"distinct": [
"vpy_data.distinct()",
"py_data.unique()",
],
}
73 changes: 1 addition & 72 deletions verticapy/tests_new/core/vdataframe/test_agg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,84 +14,13 @@
See the License for the specific language governing
permissions and limitations under the License.
"""
from collections import namedtuple
from contextlib import nullcontext as does_not_raise
import pytest
import numpy as np
from scipy.stats import median_abs_deviation, jarque_bera
from verticapy.errors import MissingColumn
import verticapy as vp
from verticapy.tests_new.core.vdataframe import REL_TOLERANCE, ABS_TOLERANCE

AggregateFun = namedtuple("AggregateFun", ["vpy", "py"])
functions = {
"aad": [
"vpy_data.aad()",
"np.absolute(py_data - py_data.mean(numeric_only=True)).mean(numeric_only=True)",
],
"count": ["vpy_data.count()", "py_data.count()"],
"cvar": [
"vpy_data.cvar()",
"py_data[py_data >= py_data.quantile(0.95, numeric_only=True)].mean(numeric_only=True)",
],
"iqr": [
"vpy_data.iqr()",
"py_data.quantile(0.75, numeric_only=True) - py_data.quantile(0.25, numeric_only=True)",
],
"kurt": ["vpy_data.kurt()", "py_data.kurt(numeric_only=True)"],
"kurtosis": [
"vpy_data.kurtosis()",
"py_data.kurtosis(numeric_only=True)",
],
"jb": ["vpy_data.jb()", "jarque_bera(py_data, nan_policy='omit').statistic"],
"mad": [
"vpy_data.mad()",
"median_abs_deviation(py_data, nan_policy='omit')",
],
"max": ["vpy_data.max()", "py_data.max(numeric_only=True)"],
"mean": ["vpy_data.mean()", "py_data.mean(numeric_only=True)"],
"avg": ["vpy_data.avg()", "py_data.mean(numeric_only=True)"],
"median": ["vpy_data.median()", "py_data.median(numeric_only=True)"],
"min": ["vpy_data.min()", "py_data.min(numeric_only=True)"],
"mode": ["vpy_data.mode()", "py_data.mode(numeric_only=True, dropna=False).values"],
"percent": ["vpy_data.percent()", "py_data.count()/len(py_data)*100"],
"quantile": [
"vpy_data.quantile(q=[0.2, 0.5])",
"py_data.quantile(q=[0.2, 0.5],numeric_only=True).values",
],
"10%": ["vpy_data.q10()", "py_data.quantile(0.1, numeric_only=True)"],
"90%": ["vpy_data.q90", "py_data.quantile(0.9, numeric_only=True)"],
"prod": ["vpy_data.prod()", "py_data.prod(numeric_only=True)"],
"product": ["vpy_data.product()", "py_data.product(numeric_only=True)"],
"range": [
"vpy_data.range()",
"py_data.max(numeric_only=True) - py_data.min(numeric_only=True)",
],
"sem": ["vpy_data.sem()", "py_data.sem(numeric_only=True)"],
"skew": ["vpy_data.skew()", "py_data.skew(numeric_only=True)"],
"skewness": ["vpy_data.skewness()", "py_data.skew(numeric_only=True)"],
"sum": ["vpy_data.sum()", "py_data.sum(numeric_only=True)"],
"std": ["vpy_data.std()", "py_data.std(numeric_only=True)"],
"stddev": ["vpy_data.stddev()", "py_data.std(numeric_only=True)"],
"topk": ["vpy_data.topk(k=3)", "py_data.value_counts(dropna=False)"],
"top1": ["vpy_data.topk(k=1)", "py_data.value_counts(dropna=False).index[0]"],
"top1_percent": [
"vpy_data.top1_percent()",
"py_data.value_counts(dropna=False).iloc[0]/len(py_data)*100",
],
"nunique": ["vpy_data.nunique(approx=False)", "py_data.nunique()"],
"unique": ["vpy_data.nunique(approx=False)", "py_data.nunique()"],
"var": ["vpy_data.var()", "py_data.var(numeric_only=True)"],
"variance": ["vpy_data.variance()", "py_data.var(numeric_only=True)"],
"value_counts": [
"vpy_data.value_counts()",
"py_data.value_counts(dropna=False)",
],
"distinct": [
"vpy_data.distinct()",
"py_data.unique()",
],
}
from verticapy.tests_new import functions, AggregateFun


class TestAgg:
Expand Down
Loading