nodes/HowToSD-ComfyUI-Data-Analysis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added Numpy Show, Numpy Squeeze, Pandas Feature Split To Numpy, Pt Show Size nodes.

Browse Source
This commit is contained in:
HowToSD
2025-02-28 19:29:52 -08:00
parent b22193dc2b
commit f207bcbcdd
15 changed files with 443 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
__init__.py
+12
View File
@@ -16,6 +16,8 @@ from .modules.matplotlib.mpl_pie_chart import MPLPieChart
from .modules.matplotlib.mpl_scatter import MPLScatter
from .modules.numpy_wrapper.numpy_float_create import NumpyFloatCreate
from .modules.numpy_wrapper.numpy_int_create import NumpyIntCreate
from .modules.numpy_wrapper.numpy_show import NumpyShow
from .modules.numpy_wrapper.numpy_squeeze import NumpySqueeze
from .modules.pandas_wrapper.pandas_add import PandasAdd
from .modules.pandas_wrapper.pandas_add_scalar_float import PandasAddScalarFloat
from .modules.pandas_wrapper.pandas_add_scalar_int import PandasAddScalarInt
@@ -46,6 +48,7 @@ from .modules.pandas_wrapper.pandas_div_series import PandasDivSeries
from .modules.pandas_wrapper.pandas_drop_duplicates import PandasDropDuplicates
from .modules.pandas_wrapper.pandas_dropna import PandasDropNA
from .modules.pandas_wrapper.pandas_exp import PandasExp
from .modules.pandas_wrapper.pandas_feature_split_to_numpy import PandasFeatureSplitToNumpy
from .modules.pandas_wrapper.pandas_fillna_scalar_float import PandasFillNAScalarFloat
from .modules.pandas_wrapper.pandas_fillna_scalar_int import PandasFillNAScalarInt
from .modules.pandas_wrapper.pandas_group_by import PandasGroupBy
@@ -178,6 +181,7 @@ from .modules.pytorch_wrapper.pt_randn import PtRandn
from .modules.pytorch_wrapper.pt_remainder import PtRemainder
from .modules.pytorch_wrapper.pt_reshape import PtReshape
from .modules.pytorch_wrapper.pt_scatter import PtScatter
from .modules.pytorch_wrapper.pt_show_size import PtShowSize
from .modules.pytorch_wrapper.pt_show_text import PtShowText
from .modules.pytorch_wrapper.pt_sin import PtSin
from .modules.pytorch_wrapper.pt_sinh import PtSinh
@@ -228,6 +232,8 @@ NODE_CLASS_MAPPINGS: Dict[str, Type[T]] = {
"MPLScatter": MPLScatter,
"NumpyFloatCreate": NumpyFloatCreate,
"NumpyIntCreate": NumpyIntCreate,
"NumpyShow": NumpyShow,
"NumpySqueeze": NumpySqueeze,
"PandasAdd": PandasAdd,
"PandasAddScalarFloat": PandasAddScalarFloat,
"PandasAddScalarInt": PandasAddScalarInt,
@@ -258,6 +264,7 @@ NODE_CLASS_MAPPINGS: Dict[str, Type[T]] = {
"PandasDropDuplicates": PandasDropDuplicates,
"PandasDropNA": PandasDropNA,
"PandasExp": PandasExp,
"PandasFeatureSplitToNumpy": PandasFeatureSplitToNumpy,
"PandasFillNAScalarFloat": PandasFillNAScalarFloat,
"PandasFillNAScalarInt": PandasFillNAScalarInt,
"PandasGroupBy": PandasGroupBy,
@@ -390,6 +397,7 @@ NODE_CLASS_MAPPINGS: Dict[str, Type[T]] = {
"PtRemainder": PtRemainder,
"PtReshape": PtReshape,
"PtScatter": PtScatter,
"PtShowSize": PtShowSize,
"PtShowText": PtShowText,
"PtSin": PtSin,
"PtSinh": PtSinh,
@@ -443,6 +451,8 @@ NODE_DISPLAY_NAME_MAPPINGS: Dict[str, str] = {
"MPLScatter": "MPL Scatter Plot",
"NumpyFloatCreate": "Numpy Float Create",
"NumpyIntCreate": "Numpy Int Create",
"NumpyShow": "Numpy Show",
"NumpySqueeze": "Numpy Squeeze",
"PandasAdd": "Pandas Add",
"PandasAddScalarFloat": "Pandas Add Scalar Float",
"PandasAddScalarInt": "Pandas Add Scalar Int",
@@ -473,6 +483,7 @@ NODE_DISPLAY_NAME_MAPPINGS: Dict[str, str] = {
"PandasDropDuplicates": "Pandas Drop Duplicates",
"PandasDropNA": "Pandas Drop NA",
"PandasExp": "Pandas Exp",
"PandasFeatureSplitToNumpy": "Pandas Feature Split To Numpy",
"PandasFillNAScalarFloat": "Pandas Fill NA Scalar Float",
"PandasFillNAScalarInt": "Pandas Fill NA Scalar Int",
"PandasGroupBy": "Pandas Group By",
@@ -605,6 +616,7 @@ NODE_DISPLAY_NAME_MAPPINGS: Dict[str, str] = {
"PtRemainder": "Pt Remainder",
"PtReshape": "Pt Reshape",
"PtScatter": "Pt Scatter",
"PtShowSize": "Pt Show Size",
"PtShowText": "Pt Show Text",
"PtSin": "Pt Sin",
"PtSinh": "Pt Sinh",
docs/images/pandas_feature_split.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 115 KiB

docs/reference/node_reference.md
+4
View File
@@ -89,6 +89,7 @@
| [Pandas Show Series](pandas_show_series.md) | Displays a Pandas Series as text. |
| [Pandas Show Text](pandas_show_text.md) | Displays a string. |
| [Pandas To String](pandas_to_string.md) | Converts a pandas DataFrame to a string representation. |
| [Pt Show Size](pt_show_size.md) | Displays PyTorch Size object as a string. |
| [Pt Show Text](pt_show_text.md) | Displays PyTorch tensor as a string. Note that the tensor is partially printed out when |
## IO
| Node | Description |
@@ -128,6 +129,8 @@
| --- | --- |
| [Numpy Float Create](numpy_float_create.md) | Creates a NumPy ndarray with 32-bit floating point precision |
| [Numpy Int Create](numpy_int_create.md) | Creates a NumPy ndarray with 32-bit integer |
| [Numpy Show](numpy_show.md) | Displays a Numpy ndarray as text. |
| [Numpy Squeeze](numpy_squeeze.md) | Removes a dimension at the specified position in the input array if it is of size 1. |
## Plot
| Node | Description |
| --- | --- |
@@ -283,6 +286,7 @@
## Transformation
| Node | Description |
| --- | --- |
| [Pandas Feature Split To Numpy](pandas_feature_split_to_numpy.md) | Splits a Pandas DataFrame into feature Numpy ndarray and label Numpy ndarray. |
| [Pandas Horizontal Concat](pandas_horizontal_concat.md) | Horizontally concatenates two pandas DataFrames. |
| [Pandas Horizontal Split](pandas_horizontal_split.md) | Horizontally splits a Pandas DataFrame into two pandas DataFrames. |
| [Pandas Join](pandas_join.md) | Merges two pandas DataFrames based on a common column. |
docs/reference/numpy_show.md
+17
View File
@@ -0,0 +1,17 @@
# Numpy Show
Displays a Numpy ndarray as text.
## Input
| Name | Data type |
|---|---|
| ndarray | Ndarray |
## Output
| Data type |
|---|
| String |
<HR>
Category: Numpy
ComfyUI Data Analysis Node Reference. © 2025 Hide Inada (HowToSD.com). All rights reserved.
docs/reference/numpy_squeeze.md
+20
View File
@@ -0,0 +1,20 @@
# Numpy Squeeze
Removes a dimension at the specified position in the input array if it is of size 1.
Specifying a tuple of dimensions is not supported.
## Input
| Name | Data type |
|---|---|
| array | Ndarray |
| dim | Int |
## Output
| Data type |
|---|
| Ndarray |
<HR>
Category: Numpy
ComfyUI Data Analysis Node Reference. © 2025 Hide Inada (HowToSD.com). All rights reserved.
docs/reference/pandas_feature_split_to_numpy.md
+24
View File
@@ -0,0 +1,24 @@
# Pandas Feature Split To Numpy
Splits a Pandas DataFrame into feature Numpy ndarray and label Numpy ndarray.
If output_1d_label is set, label will be output as a 1d array instead of a 2d array.
As shown in the below screenshot, this node can replace multiple nodes that are used to split Pandas DataFrame into two DataFrames, convert to NumPy, then squeeze the label data.
![Pandas Feature Split To Numpy](../images/pandas_feature_split.png)
## Input
| Name | Data type |
|---|---|
| dataframe | DataFrame |
| label_integer_position | Int |
| output_1d_label | Boolean |
## Output
| Data type |
|---|
| Ndarray |
| Ndarray |
<HR>
Category: Transformation
ComfyUI Data Analysis Node Reference. © 2025 Hide Inada (HowToSD.com). All rights reserved.
docs/reference/pt_show_size.md
+17
View File
@@ -0,0 +1,17 @@
# Pt Show Size
Displays PyTorch Size object as a string.
## Input
| Name | Data type |
|---|---|
| size | Ptsize |
## Output
| Data type |
|---|
| String |
<HR>
Category: Display data
ComfyUI Data Analysis Node Reference. © 2025 Hide Inada (HowToSD.com). All rights reserved.
modules/numpy_wrapper/numpy_show.py
+57
View File
@@ -0,0 +1,57 @@
"""
This code is based on
https://github.com/pythongosssss/ComfyUI-Custom-Scripts/blob/main/py/show_text.py
See credit/credit.md for the full license.
"""
import numpy as np
class NumpyShow:
"""
Displays a Numpy ndarray as text.
category: Numpy
"""
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"ndarray": ("NDARRAY", {}),
},
"hidden": {
"unique_id": "UNIQUE_ID",
"extra_pnginfo": "EXTRA_PNGINFO",
},
}
INPUT_IS_LIST = True
RETURN_TYPES = ("STRING",)
FUNCTION = "notify"
OUTPUT_NODE = True
OUTPUT_IS_LIST = (True,)
CATEGORY = "Data Analysis"
def notify(self, ndarray, unique_id=None, extra_pnginfo=None):
text = None
if unique_id is not None and extra_pnginfo is not None:
if not isinstance(extra_pnginfo, list):
print("Error: extra_pnginfo is not a list")
elif (
not isinstance(extra_pnginfo[0], dict)
or "workflow" not in extra_pnginfo[0]
):
print("Error: extra_pnginfo[0] is not a dict or missing 'workflow' key")
else:
ind = ndarray[0]
text = [str(ind)] # wrap in list
workflow = extra_pnginfo[0]["workflow"]
node = next(
(x for x in workflow["nodes"] if str(x["id"]) == str(unique_id[0])),
None,
)
if node:
node["widgets_values"] = [text]
else:
print("unique_id or extra_pnginfo is None.")
return {"ui": {"text": text}, "result": (text,)}
modules/numpy_wrapper/numpy_squeeze.py
+45
View File
@@ -0,0 +1,45 @@
from typing import Any, Dict
import numpy as np
class NumpySqueeze:
"""
Removes a dimension at the specified position in the input array if it is of size 1.
Specifying a tuple of dimensions is not supported.
category: Numpy
"""
@classmethod
def INPUT_TYPES(cls) -> Dict[str, Any]:
"""
Defines the input types for the function.
Returns:
Dict[str, Any]: A dictionary specifying required input types.
"""
return {
"required": {
"array": ("NDARRAY", {}),
"dim": ("INT", {"default": -1, "min": -1, "max": 10})
}
}
RETURN_TYPES: tuple = ("NDARRAY",)
FUNCTION: str = "f"
CATEGORY: str = "Data Analysis"
def f(self, array: np.ndarray, dim: int) -> tuple:
"""
Removes a dimension at the specified position in the input array if it is of size 1.
Args:
array (np.ndarray): Input array.
dim (int): Dimension to remove if it is of size 1.
Returns:
tuple: A tuple containing the transformed NumPy array.
"""
ar_out = np.squeeze(array, dim)
return (ar_out,)
modules/pandas_wrapper/pandas_feature_split_to_numpy.py
+71
View File
@@ -0,0 +1,71 @@
from typing import Any, Dict
import pandas as pd
import numpy as np
class PandasFeatureSplitToNumpy:
"""
Splits a Pandas DataFrame into feature Numpy ndarray and label Numpy ndarray.
If output_1d_label is set, label will be output as a 1d array instead of a 2d array.
As shown in the below screenshot, this node can replace multiple nodes that are used to split Pandas DataFrame into two DataFrames, convert to NumPy, then squeeze the label data.
![Pandas Feature Split To Numpy](../images/pandas_feature_split.png)
category: Transformation
"""
@classmethod
def INPUT_TYPES(cls) -> Dict[str, Any]:
"""
Defines the input types for the function.
Returns:
Dict[str, Any]: A dictionary specifying required input types.
"""
return {
"required": {
"dataframe": ("DATAFRAME", {}),
"label_integer_position": ("INT", {"default": -1, "min": -10, "max": 1024}),
"output_1d_label": ("BOOLEAN", {"default": True})
}
}
RETURN_TYPES: tuple = ("NDARRAY", "NDARRAY")
RETURN_NAMES: tuple = ("feature", "label")
FUNCTION: str = "f"
CATEGORY: str = "Data Analysis"
def f(self, dataframe: pd.DataFrame,
label_integer_position: int,
output_1d_label: bool) -> tuple:
"""
Splits a Pandas DataFrame into feature Numpy ndarray and label Numpy ndarray.
Args:
dataframe (pd.DataFrame): The DataFrame to split.
label_integer_position (int): The column integer position of the label.
output_1d_label (bool): If output_1d_label is set, label will be output as a 1d array instead of a 2d array.
Returns:
tuple: A tuple containing the feature and label arrays.
"""
num_columns = dataframe.shape[1]
if label_integer_position < 0:
label_integer_position += num_columns
# Validate label_integer_position
if label_integer_position >= num_columns:
raise ValueError(f"label_integer_position {label_integer_position} is out of range for dataframe with {num_columns} columns.")
# Extract features
np_left = dataframe.iloc[:, :label_integer_position].to_numpy()
np_right = dataframe.iloc[:, label_integer_position + 1:].to_numpy() if label_integer_position < num_columns - 1 else np.empty((len(dataframe), 0))
np_features = np.hstack([np_left, np_right]) if np_right.shape[1] > 0 else np_left
# Extract label
np_label = dataframe.iloc[:, label_integer_position].to_numpy()
if output_1d_label:
np_label = np_label.ravel()
return (np_features, np_label)
modules/pytorch_wrapper/pt_show_size.py
+60
View File
@@ -0,0 +1,60 @@
"""
Almost all of this code was taken from
https://github.com/pythongosssss/ComfyUI-Custom-Scripts/blob/main/py/show_text.py
See credit/credit.md for the full license.
"""
from typing import List
import torch
class PtShowSize:
"""
Displays PyTorch Size object as a string.
category: Display data
"""
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"size": ("PTSIZE", {}),
},
"hidden": {
"unique_id": "UNIQUE_ID",
"extra_pnginfo": "EXTRA_PNGINFO",
},
}
INPUT_IS_LIST = True
RETURN_TYPES = ("STRING",)
FUNCTION = "notify"
OUTPUT_NODE = True
OUTPUT_IS_LIST = (True,)
CATEGORY = "Data Analysis"
MAX_NUM_ELEMENTS_TO_DISPLAY = 100
def notify(self, size: torch.Size, unique_id=None, extra_pnginfo=None):
text = str(size[0])
if unique_id is not None and extra_pnginfo is not None:
if not isinstance(extra_pnginfo, list):
print("Error: extra_pnginfo is not a list")
elif (
not isinstance(extra_pnginfo[0], dict)
or "workflow" not in extra_pnginfo[0]
):
print("Error: extra_pnginfo[0] is not a dict or missing 'workflow' key")
else:
workflow = extra_pnginfo[0]["workflow"]
node = next(
(x for x in workflow["nodes"] if str(x["id"]) == str(unique_id[0])),
None,
)
if node:
node["widgets_values"] = [text]
else:
print("unique_id or extra_pnginfo is None.")
return {"ui": {"text": [text]}, "result": ([text],)}
pyproject.toml
+1 -1
View File
@@ -1,7 +1,7 @@
[project]
name = "data-analysis"
description = "Data analysis custom modules for ComfyUI - Use Pandas & Matplotlib within ComfyUI"
version = "1.4.2"
version = "1.4.3"
license = {file = "LICENSE"}
[project.urls]
tests/numpy_wrapper/numpy_squeeze_test.py
+58
View File
@@ -0,0 +1,58 @@
import os
import sys
import unittest
import numpy as np
PROJECT_ROOT = os.path.realpath(os.path.join(os.path.dirname(__file__), "..", ".."))
MODULE_ROOT = os.path.join(PROJECT_ROOT, "modules")
sys.path.append(MODULE_ROOT)
from numpy_wrapper.numpy_squeeze import NumpySqueeze # Importing the NumpySqueeze class
class TestNumpySqueeze(unittest.TestCase):
def setUp(self):
"""Set up test instance."""
self.node = NumpySqueeze()
# Define test cases: (input_array, dim, expected_shape)
self.test_cases = [
# Case 1: Squeezing a singleton dimension
(np.ones((1, 3, 4)), 0, (3, 4)), # (1,3,4) -> (3,4)
(np.ones((2, 1, 4)), 1, (2, 4)),
(np.ones((100, 1)), 1, (100, )),
# Case 2: Multiple singleton dimensions, squeezing one
(np.ones((1, 2, 1, 4)), 2, (1, 2, 4)),
# Case 3: Squeezing a negative index
(np.ones((2, 3, 1)), -1, (2, 3)),
# Case 4: Squeezing all size 1 dimensions
(np.ones((1, 1, 1)), 0, (1, 1)),
(np.ones((1, 1, 1)), 1, (1, 1)),
(np.ones((1, 1, 1)), 2, (1, 1)),
# Case 5: Squeezing a 1d array with a single element to a scalar
(np.ones((1,)), 0, ()),
]
def test_squeeze(self):
"""Test array squeeze operation on various dimensions."""
for input_array, dim, expected_shape in self.test_cases:
with self.subTest(input_shape=input_array.shape, dim=dim):
result, = self.node.f(input_array, dim)
# Ensure return value is a array
self.assertTrue(isinstance(result, np.ndarray), "Output is not a array")
# Ensure result has correct shape
self.assertEqual(result.shape, expected_shape, f"Expected shape {expected_shape}, got {result.shape}")
# Ensure result has the same dtype
self.assertEqual(result.dtype, input_array.dtype, "Dtype mismatch after squeeze operation")
if __name__ == "__main__":
unittest.main()
tests/pandas_wrapper/pandas_feture_split_to_numpy_test.py
+55
View File
@@ -0,0 +1,55 @@
import os
import sys
import unittest
import numpy as np
import pandas as pd
PROJECT_ROOT = os.path.realpath(os.path.join(os.path.dirname(__file__), "..", ".."))
MODULE_ROOT = os.path.join(PROJECT_ROOT, "modules")
sys.path.append(MODULE_ROOT)
from pandas_wrapper.pandas_feature_split_to_numpy import PandasFeatureSplitToNumpy
class TestPandasFeatureSplitToNumpy(unittest.TestCase):
def setUp(self):
"""Set up test data."""
self.node = PandasFeatureSplitToNumpy()
# Sample DataFrame
self.df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
})
def test_feature_split_last_column_label_0(self):
"""Test splitting with the last column as the label."""
features, labels = self.node.f(self.df, label_integer_position=0, output_1d_label=True)
np.testing.assert_array_equal(features, np.array([[4, 7], [5, 8], [6, 9]]))
np.testing.assert_array_equal(labels, np.array([1, 2, 3]))
def test_feature_split_last_column_label_1(self):
"""Test splitting with the last column as the label."""
features, labels = self.node.f(self.df, label_integer_position=1, output_1d_label=True)
np.testing.assert_array_equal(features, np.array([[1, 7], [2, 8], [3, 9]]))
np.testing.assert_array_equal(labels, np.array([4, 5, 6]))
def test_feature_split_last_column_label_2(self):
"""Test splitting with the last column as the label."""
features, labels = self.node.f(self.df, label_integer_position=2, output_1d_label=True)
np.testing.assert_array_equal(features, np.array([[1, 4], [2, 5], [3, 6]]))
np.testing.assert_array_equal(labels, np.array([7, 8, 9]))
def test_feature_split_last_column_label_negative_1(self):
"""Test splitting with the last column as the label."""
features, labels = self.node.f(self.df, label_integer_position=-1, output_1d_label=True)
np.testing.assert_array_equal(features, np.array([[1, 4], [2, 5], [3, 6]]))
np.testing.assert_array_equal(labels, np.array([7, 8, 9]))
if __name__ == "__main__":
unittest.main()
web/js/ShowSeries.js → web/js/ShowTextGeneric.js
+2 -2
View File
@@ -10,9 +10,9 @@ import { ComfyWidgets } from "../../../scripts/widgets.js";
// Displays input text on a node
app.registerExtension({
name: "HowToSD.ShowSeries",
name: "HowToSD.ShowTextGeneric",
async beforeRegisterNodeDef(nodeType, nodeData, app) {
if (["PtShowText", "PandasShowSeries"].includes(nodeData.name)) { // This needs to match NODE_CLASS_MAPPINGS in Python
if (["NumpyShow", "PtShowText", "PtShowSize", "PandasShowSeries"].includes(nodeData.name)) { // This needs to match NODE_CLASS_MAPPINGS in Python
function populate(text) {
if (this.widgets) {
// Clear all widgets on the node