It seems simplistic as a task to perform, but I've been having hard time to add a border frame to my excel-written table (using xlsxwriter engine). The only way I could do so is by getting the size of my df & starting row/column then loop on each cell and format it, which is redundant. Is there a solution I'm not seeing ? I tried the styleframe module in vain.
Reproducible example:
import pandas as pd
import numpy as np
from styleframe import StyleFrame, Styler, utils
df = pd.DataFrame(np.random.randint(0,100,size=(100, 2)), columns=list('AB'))
df = df.style.set_properties(**{'text-align': 'center'})
writer = StyleFrame.ExcelWriter("Test.xlsx", engine='xlsxwriter')
df.to_excel(writer, sheet_name= 'Random', index=False)
format_x = workbook.add_format({'border': 2})
worksheet.set_column('A:B',20,format_x)
writer.save()
Related
I've been playing with Titanic dataset and working through some visualisations in Pandas using this tutorial. https://www.kdnuggets.com/2023/02/5-pandas-plotting-functions-might-know.html
I have a visual of scatterplot having used this code.
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
df = pd.read_csv('train.csv')
I was confused by bootstrap plot result so went on to scatterplot.
pd.plotting.scatter_matrix(df, figsize=(10,10), )
plt.show()
I can sort of interpret it but I'd like to put the various variables at top and bottom of every column. Is that doable?
You can use:
fig, ax = plt.subplots(4, 3, figsize=(20, 15))
sns.scatterplot(x = 'bedrooms', y = 'price', data = dataset, whis=1.5, ax=ax[0, 0])
sns.scatterplot(x = 'bathrooms', y = 'price', data = dataset, whis=1.5, ax=ax[0, 1])
I was wondering how one would create a 3D scatter chart in Taipy.
I tried this code initially:
import pandas as pd
import numpy as np
from taipy import Gui
df = pd.DataFrame(np.random.randint(0,100,size=(100, 3)), columns=list('xyz'))
df['cluster1']=np.random.randint(0,3,100)
my_page ="""
Creation of a 3-D chart:
<|{df}|chart|type=Scatter3D|x=x|y=y|z=z|mode=markers|color=cluster|>
"""
Gui(page=my_page).run()
This does indeed display a 3D plot, but the colors (clusters) do not show up.
Any hint?
Yes, you need some massaging of your dataframes to do it.
Here's a sample code that achieves this:
import pandas as pd
import numpy as np
from taipy import Gui
df = pd.DataFrame(np.random.randint(0,100,size=(100, 3)), columns=list('xyz'))
df['cluster1']=np.random.randint(0,3,100)
# Create a list of 3 dataframes, one per cluster
datas = [df[df['cluster1']==i] for i in range(3)]
properties = {
}
# create dynamically the property list.
# str(i) points to a dataframe index
# "/x" points to the column value in the selected dataframe
for i in range(len(datas)):
properties[f"x[{i+1}]"] = str(i)+"/x"
properties[f"y[{i+1}]"] = str(i)+"/y"
properties[f"z[{i+1}]"] = str(i)+"/z"
properties[f'name[{i+1}]'] = str(i+1)
print(properties)
chart = "<|{datas}|chart|type=Scatter3D|properties={properties}|mode=markers|height=800px|>"
Gui(page=chart).run()
In fact, with the new release: Taipy 1.1, this is very easy to do in a few lines of code:
import pandas as pd
import numpy as np
from taipy import Gui
color_map={0:"blue",1:'green', 2:"red"}
df = pd.DataFrame(np.random.randint(0,100,size=(100, 3)), columns=list('xyz'))
df['cluster1'] = np.random.randint(0,3,100)
df['cluster_colors'] = df.apply(lambda row: color_map[row.cluster1], axis=1)
marker = {"color":"cluster_colors"}
chart = "<|{df}|chart|type=Scatter3D|x=x|y=y|z=z|marker={marker}|mode=markers|height=800px|>"
Gui(page=chart).run()
If you want to leave it to Taipy to pick the colors for you, then you can simply use:
import pandas as pd
import numpy as np
from taipy import Gui
df = pd.DataFrame(np.random.randint(0,100,size=(100, 3)), columns=list('xyz'))
df['cluster1'] = np.random.randint(0,3,100)
marker = {"color":"cluster1"}
chart = "<|{df}|chart|type=Scatter3D|x=x|y=y|z=z|marker={marker}|mode=markers|height=800px|>"
Gui(page=chart).run()
I am having an issue where I cannot format my tables. The text is too long to just edit the dimensions or the text size. How can I quickly change this so you can see all the text when I have the data for each column more filled in? I am looking for a wrap text kind of function but I don't know if that is possible the way I'm doing it. Is there another way you'd recommend? I'm changing the table into a .png to insert into an Excel file. It has to be a .png so it's an object and doesn't mess with the size of the rows and columns in Excel.
import matplotlib.pyplot as plt
import xlsxwriter as xl
import numpy as np
import yfinance as yf
import pandas as pd
import datetime as dt
import mplfinance as mpf
import pandas_datareader
from pandas_datareader import data as pdr
yf.pdr_override()
import numpy as np
Individualreport = "C:\\Users\\Ashley\\FromPython.xlsx"
Ticklist = pd.read_excel("C:\\Users\\Ashley\\Eyes Trial Data Center.xlsx",sheet_name='Tickers', header=None)
stocks = Ticklist.values.ravel()
PipelineData = pd.read_excel("C:\\Users\\Ashley\\Eyes Trial Data Center.xlsx", sheet_name='Pipeline', header=None)
writer = pd.ExcelWriter(Individualreport, engine='xlsxwriter')
for i in stocks:
#write pipeline data
t = PipelineData.loc[(PipelineData[0]==i)]
print(t)
def render_mpl_table(data, col_width=10, row_height=1, font_size=10, wrap=True,
header_color='#40466e', row_colors=['#f1f1f2', 'w'], edge_color='w',
bbox=[0, 0, 1, 1], header_columns=0,
ax=None, **kwargs):
if ax is None:
size = (np.array(data.shape[::-1]) + np.array([0, 1])) * np.array([col_width, row_height])
fig, ax = plt.subplots(figsize=size)
ax.axis('off')
mpl_table = ax.table(cellText=data.values, bbox=bbox, colLabels=data.columns, **kwargs)
mpl_table.auto_set_font_size(False)
#mpl_table.set_fontsize(font_size)
for k, cell in mpl_table._cells.items():
cell.set_edgecolor(edge_color)
if k[0] == 0 or k[1] < header_columns:
cell.set_text_props(weight='bold', color='w')
cell.set_facecolor(header_color)
else:
cell.set_facecolor(row_colors[k[0]%len(row_colors) ])
return ax.get_figure(), ax
fig,ax = render_mpl_table(t, header_columns=0, col_width=2.0)
fig.savefig(str(i)+'pipe.png')
I think I needed to use an additional package, haven't tried with this example, but worked in another similar example I did.
from textwrap import wrap
label = ("label text that is getting put in the graph")
label = [ '\n'.join(wrap(l, 20)) for l in label ]
#20 is number of characters per line
I have a graph which I plotted and saved as PDF in my drive. Now I want to add a dataframe (5 columns) as second page to that PDF. How can it be done?
I searched a lot but couldnt find great solution. Is there any method to save in existing PDF or any method to save dataframe in new PDF?
Use PDFPages. Each time you call plt.close() you will get a new page. So, draw your figure, call plt.close(), then draw the Pandas dataframe as a table using ax.table() and then call plt.close() again.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
def _draw_as_table(df, pagesize):
alternating_colors = [['white'] * len(df.columns), ['lightgray'] * len(df.columns)] * len(df)
alternating_colors = alternating_colors[:len(df)]
fig, ax = plt.subplots(figsize=pagesize)
ax.axis('tight')
ax.axis('off')
the_table = ax.table(cellText=df.values,
rowLabels=df.index,
colLabels=df.columns,
rowColours=['lightblue']*len(df),
colColours=['lightblue']*len(df.columns),
cellColours=alternating_colors,
loc='center')
return fig
def dataframe_to_pdf(df, filename, pagesize=(11, 8.5)):
with PdfPages(filename) as pdf:
# page 1: draw your current figure
...
plt.close()
# page 2: draw the table
fig = _draw_as_table(page, pagesize)
pdf.savefig(fig, bbox_inches='tight')
plt.close()
I am fetching excel data from django database via raw query. excel is generated but column header is missing .
please suggest some way to get that header.
import pandas as pd
from pandas import ExcelWriter
df1 = pd.DataFrame(row1)
try:
from StringIO import StringIO
except:
from io import StringIO
import xlwt
wb = Workbook()
writer = ExcelWriter("XYZ.xlsx",options={'remove_timezone': True})
xl_out = StringIO()
writer.path = xl_out
ws1 = wb.add_sheet("abc")
for col_num, value in enumerate(df1.columns.values):
ws1.write(1,col_num + 1, 'value')
df1.to_excel(writer,"abc", index= True, header=True)
writer.save()