Pandas style.background_gradient ignore NaN - python

I have the following code to dump the dataframe results into a table in HTML, such that the columns in TIME_FRAMES are colored according to a colormap from seaborn.
import seaborn as sns
TIME_FRAMES = ["24h", "7d", "30d", "1y"]
# Set CSS properties for th elements in dataframe
th_props = [
('font-size', '11px'),
('text-align', 'center'),
('font-weight', 'bold'),
('color', '#6d6d6d'),
('background-color', '#f7f7f9')
]
# Set CSS properties for td elements in dataframe
td_props = [
('font-size', '11px')
]
cm = sns.light_palette("green", as_cmap=True)
s = (results.style.background_gradient(cmap=cm, subset=TIME_FRAMES)
.set_table_styles(styles))
a = s.render()
with open("test.html", "w") as f:
f.write(a)
From this, I get the warning:
/python3.7/site-packages/matplotlib/colors.py:512: RuntimeWarning:
invalid value encountered in less xa[xa < 0] = -1
And, as you can see in the picture below, the columns 30d and 1y don't get rendered correctly, as they have NaN's. How can I just make it so that the NaN's are ignored and the colors are rendered only using the valid values? Setting the NaN's to 0 is not a valid option, as NaN's here have a meaning by themselves.

A bit late, but for future reference.
I had the same problem, and here is how I solved it:
import pandas as pd
import numpy as np
dt = pd.DataFrame({'col1': [1,2,3,4,5], 'col2': [4,5,6,7,np.nan], 'col3': [8,2,6,np.nan,np.nan]})
First fill in the nas with a big value
dt.fillna(dt.max().max()+1, inplace=True)
Function to color the font of this max value white
def color_max_white(val, max_val):
color = 'white' if val == max_val else 'black'
return 'color: %s' % color
Function to color the background of the maximum value white
def highlight_max(data, color='white'):
attr = 'background-color: {}'.format(color)
if data.ndim == 1: # Series from .apply(axis=0) or axis=1
is_max = data == data.max()
return [attr if v else '' for v in is_max]
else: # from .apply(axis=None)
is_max = data == data.max().max()
return pd.DataFrame(np.where(is_max, attr, ''),
index=data.index, columns=data.columns)
Putting everything together
max_val = dt.max().max()
dt.style.format("{:.2f}").background_gradient(cmap='Blues', axis=None).applymap(lambda x: color_max_white(x, max_val)).apply(highlight_max, axis=None)
This link helped me for the answer

this works fine for me
df.style.applymap(lambda x: 'color: transparent' if pd.isnull(x) else '')

#quant 's answer almost worked for me but my background gradient would still use the max value to calculate the color gradient. I implemented #night-train 's suggestion to set the color map, then used two functions:
import copy
cmap = copy.copy(plt.cm.get_cmap("Blues"))
cmap.set_under("white")
def color_nan_white(val):
"""Color the nan text white"""
if np.isnan(val):
return 'color: white'
def color_nan_white_background(val):
"""Color the nan cell background white"""
if np.isnan(val):
return 'background-color: white'
And then applied them to my dataframe again borrowing from #quant with a slight modification for ease:
(df.style
.background_gradient(axis='index')
.applymap(lambda x: color_nan_white(x))
.applymap(lambda x: color_nan_white_background(x))
)
Then it worked perfectly.

Related

using applymap method to color cells based on condition

I would like to color some cells (in a data frame) based on their content using pandas, I did some tries but with no required results
this is my last failed try :
import pandas as pd
import dataframe_image as dfi
df = pd.read_excel('splice traitment.xlsx', sheet_name='Sheet4', usecols="B,C,D,E,F,G,H,I,J,K")
def color_cells(val):
color = 'red' if val == 7 else ''
return 'background-color: {}'.format(color)
df.style.applymap(color_cells)
dfi.export(df,"table.png")
Thank you very much
You can pass styled DataFrame to export method:
dfi.export(df.style.applymap(color_cells),"table.png")
Or asign to variable styled:
styled = df.style.applymap(color_cells)
dfi.export(styled,"table.png")

comparing two columns and highlighting differences in dataframe

What would be the best way to compare two columns and highlight if there is a difference between two columns in dataframe?
df = pd.DataFrame({'ID':['one2', 'one3', 'one3', 'one4' ],
'Volume':[5.0, 6.0, 7.0, 2.2],
'BOX':['one','two','three','four'],
'BOX2':['one','two','five','one hundred']})
I am trying to compare the BOX column and BOX2 column and I'd like to highlight the differences between them.
Maybe you can do something like this:
df.style.apply(lambda x: (x != df['BOX']).map({True: 'background-color: red; color: white', False: ''}), subset=['BOX2'])
Output (in Jupyter):
You might try something like:
def hl(d):
df = pd.DataFrame(columns=d.columns, index=d.index)
df.loc[d['BOX'].ne(d['BOX2']), ['BOX', 'BOX2']] = 'background: yellow'
return df
df.style.apply(hl, axis=None)
output:
for the whole row:
def hl(d):
df = pd.DataFrame(columns=d.columns, index=d.index)
df.loc[d['BOX'].ne(d['BOX2'])] = 'background: yellow'
return df
df.style.apply(hl, axis=None)
output:

Apply multiple styles to cell in pandas

So, basically I want to apply styles to cell and render to html.
This is what I have done so far:
import pandas as pd
import numpy as np
data = [dict(order='J23-X23', num=5, name='foo', value='YES'),
dict(order='Y23-X24', num=-4, name='bar', value='NO'),
dict(order='J24-X24', num=6, name='baz', value='NO'),
dict(order='X25-X24', num=-2, name='foobar', value='YES')]
df = pd.DataFrame(data)
def condformat(row):
cellBGColor = 'green' if row.value == 'YES' else 'blue'
color = 'background-color: {}'.format(cellBGColor)
return (color, color, color, color)
s = df.style.apply(condformat, axis=1)
with open('c:/temp/test.html', 'w') as f:
f.write(s.render())
My problem is two fold:
(1) Am I using the right rendering? Or is there a better way to do this? As in what does to_html give me?
(2) What if I have to add another style, say make -ve numbers in the format (35) in red color?
So, after battling with trial-error:
s = df.style.apply(condformat, axis=1).applymap(dataframe_negative_coloring)
with a new method:
def dataframe_negative_coloring(value):
''' Colors Dataframe rows with alternate colors.'''
color = 'red' if value < 0 else 'black'
return 'color: %s' % color
Any purists out there, feel free to advice if I can make this better

Highlight the maximum value in the dataframe and save as csv

enter code here I have code, where I am able to generate the maximum value, but I need to highlight that maximum value (or at least cell address of that value).
I tried to apply the style, but it is throwing some error:
AttributeError: module 'numpy' has no attribute 'style'
My code would be like this :
import pandas as pd
import numpy as np
dataset = pd.read_csv("ALL_CURVES.csv")
dataset['groups'] = dataset.index//192
Results=dataset.groupby('groups').max()
Results['groups'] = Results.index//20
outgrid=Results.iloc[:,1].values
#####
X=outgrid
x=np.array(X)
output=np.reshape(x, (9,-1 ))
max_output=output.max()
np.amax(output, axis=None, out=None)
np.style.apply(highlight_max, color='darkorange', axis=1)
#####
#print(output)
np.savetxt('output.csv', output,fmt="%2.2f", delimiter=',')
You can do something like this:
df = pd.DataFrame({'A':['15.45','78.7456','79.24', '75.45'],
'B':['78.6','45.23','45.4', '34.45'],
'C':['8.6','5.23','5.4', '4.45']})
print (df)
def highlight_max(data, color='red'):
attr = 'background-color: {}'.format(color)
data = data.astype(float)
if data.ndim == 1:
is_max = data == data.max()
return [attr if v else '' for v in is_max]
else:
is_max = data == data.max().max()
return pd.DataFrame(np.where(is_max, attr, ''),
index=data.index, columns=data.columns)
This highlights the maximum values in the dataframe
And with this you can save it to excel.
df = df.style.apply(highlight_max)
print(df)
dfPercent.to_excel('file.xlsx')
A similar answer is here Python Pandas - Highlighting maximum value in column

Pandas style: How to highlight diagonal elements

I was wondering how to highlight diagonal elements of pandas dataframe using df.style method.
I found this official link where they discuss how to highlight maximum value, but I am having difficulty creating function to highlight the diagonal elements.
Here is an example:
import numpy as np
import pandas as pd
df = pd.DataFrame({'a':[1,2,3,4],'b':[1,3,5,7],'c':[1,4,7,10],'d':[1,5,9,11]})
def highlight_max(s):
'''
highlight the maximum in a Series yellow.
'''
is_max = s == s.max()
return ['background-color: yellow' if v else '' for v in is_max]
df.style.apply(highlight_max)
This gives following output:
I am wanting a yellow highlight across the diagonal elements 1,3,7,11 only.
How to do that?
Using axis=None we can use numpy to easily set the diagonal styles (Credit for this goes to #CJR)
import numpy as np
import pandas as pd
def highlight_diag(df):
a = np.full(df.shape, '', dtype='<U24')
np.fill_diagonal(a, 'background-color: yellow')
return pd.DataFrame(a, index=df.index, columns=df.columns)
df.style.apply(highlight_diag, axis=None)
Original, really hacky solution
a = np.full(df.shape, '', dtype='<U24')
np.fill_diagonal(a, 'background-color: yellow')
df_diag = pd.DataFrame(a,
index=df.index,
columns=df.columns)
def highlight_diag(s, df_diag):
return df_diag[s.name]
df.style.apply(highlight_diag, df_diag=df_diag)
The trick is to use the axis=None parameter of the df.style.apply function in order to access the entire dataset:
import numpy as np
import pandas as pd
df = pd.DataFrame({'a':[1,2,3,4],'b':[1,3,5,7],'c':[1,4,7,10],'d':[1,5,9,11]})
def highlight_diag(data, color='yellow'):
'''
highlight the diag values in a DataFrame
'''
attr = 'background-color: {}'.format(color)
# create a new dataframe of the same structure with default style value
df_style = data.replace(data, '')
# fill diagonal with highlight color
np.fill_diagonal(df_style.values, attr)
return df_style
df.style.apply(highlight_diag, axis=None)
The other answer is pretty good but I already wrote this so....
def style_diag(data):
diag_mask = pd.DataFrame("", index=data.index, columns=data.columns)
min_axis = min(diag_mask.shape)
diag_mask.iloc[range(min_axis), range(min_axis)] = 'background-color: yellow'
return diag_mask
df = pd.DataFrame({'a':[1,2,3,4],'b':[1,3,5,7],'c':[1,4,7,10],'d':[1,5,9,11]})
df.style.apply(style_diag, axis=None)

Categories