AttributeError: 'DataFrame' object has no attribute 'plot_coordinates'

Question

I would like to plot a graph using python showing variables on X/Y axis after applying MCA. I tried this code but returns the following error:

AttributeError: 'DataFrame' object has no attribute 'plot_coordinates'

This is the code:

ax = mca.plot_coordinates(
X=X,
ax=None,
figsize=(6, 6),
show_row_points=True,
row_points_size=10,
show_row_labels=False,
show_column_points=True,
column_points_size=30,
show_column_labels=False,
legend_n_cols=1)

Can anyone help please?

Thanks,

What is mca? A pandas.DataFrame object? The error is accurate; pandas.DataFrame doesn't have an attribute plot_coordinates. — Ben
– Ben, Commented Aug 29, 2019 at 9:06
mca stands for multiple correspondence analysis. I have a dataframe named 'train' with many columns and I applied the mca on it using mca = mca.fit(train). This gives the principal components of the mca then I would like to plot the train variables on (x,y) graph while x is the 1st component and y is the second — k_bm
– k_bm, Commented Aug 29, 2019 at 9:13
It's always nice to provide a complete working example. In other cases, people are forced to guess. So, if we have to follow this route, what is the output of type(mca)? — nostradamus
– nostradamus, Commented Aug 29, 2019 at 10:54

cheng yang · Accepted Answer · 2020-10-29 08:55:23Z

mca = prince.MCA()

typeof mca is prince.mca.MCA ,it has the method . if you add the code,

mca = mca.fit(X) # same as calling ca.fs_r(1)
mca = mca.transform(X)

type of mca is DataFrame.it do not have the method plot_coordinates. The right code:

import pandas as pd 
import prince

X = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/balloons/adult+stretch.data')
X.columns = ['Color', 'Size', 'Action', 'Age', 'Inflated']

print(X.head())

mca = prince.MCA()

mca = mca.fit(X) # same as calling ca.fs_r(1)
mca1 = mca.transform(X) # same as calling ca.fs_r_sup(df_new) for *another* test set.
print(mca1)

ax = mca.plot_coordinates(
     X=X,
     ax=None,
     figsize=(6, 6),
     show_row_points=True,
     row_points_size=10,
     show_row_labels=False,
     show_column_points=True,
     column_points_size=30,
     show_column_labels=False,
     legend_n_cols=1
     )

ax.get_figure().savefig('./mca_coordinates.svg')

Normie · Accepted Answer · 2019-11-13 16:30:04Z

0

I don't know if this helps but I ran into that same error. To fix it, I specified the X= to be the exact dataframe and columns/variables and it fixed the problem: X=train[variables] instead of X=X

ax = mca.plot_coordinates(
X=train[variables],
ax=None,
figsize=(6, 6),
show_row_points=True,
row_points_size=10,
show_row_labels=False,
show_column_points=True,
column_points_size=30,
show_column_labels=False,
legend_n_cols=1)

answered Nov 13, 2019 at 16:30

Normie

162 bronze badges

Collectives™ on Stack Overflow

AttributeError: 'DataFrame' object has no attribute 'plot_coordinates'

2 Answers 2

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related