sklearn plot confusion matrix with labels

Question

I want to plot a confusion matrix to visualize the classifer s performance  but it shows only the numbers of the labels  not the labels themselves   from sklearn metrics import confusion matrix import pylab as pl y test   business    business    business    business    business    business    business    business    business    business    business    business    business    business    business    business    business    business    business    business    pred array   health    business    business    business    business           business    health    health    business    business    business           business    business    business    business    business           health    health    business    health           dtype   S8    cm   confusion matrix y test  pred  pl matshow cm  pl title  Confusion matrix of the classifier   pl colorbar   pl show     How can I add the labels  health  business  etc  to the confusion matrix

User · Accepted Answer

As hinted in this question  you have to  open  the lower-level artist API  by storing the figure and axis objects passed by the matplotlib functions you call  the fig  ax and cax variables below   You can then replace the default x- and y-axis ticks using set xticklabels set yticklabels   from sklearn metrics import confusion matrix  labels     business    health   cm   confusion matrix y test  pred  labels  print cm  fig   plt figure   ax   fig add subplot 111  cax   ax matshow cm  plt title  Confusion matrix of the classifier   fig colorbar cax  ax set xticklabels        labels  ax set yticklabels        labels  plt xlabel  Predicted   plt ylabel  True   plt show     Note that I passed the labels list to the confusion matrix function to make sure it s properly sorted  matching the ticks   This results in the following figure

User · Answer

UPDATE   In scikit-learn 0 22  there s a new feature to plot the confusion matrix directly   See the documentation  sklearn metrics plot confusion matrix    OLD ANSWER   I think it s worth mentioning the use of seaborn heatmap here   import seaborn as sns import matplotlib pyplot as plt       ax  plt subplot   sns heatmap cm  annot True  ax   ax    annot True to annotate cells    labels  title and ticks ax set xlabel  Predicted labels   ax set ylabel  True labels     ax set title  Confusion Matrix     ax xaxis set ticklabels   business    health     ax yaxis set ticklabels   health    business

User · Answer

To add to  akilat90 s update about sklearn metrics plot confusion matrix  You can use the ConfusionMatrixDisplay class within sklearn metrics directly and bypass the need to pass a classifier to plot confusion matrix  It also has the display labels argument  which allows you to specify the labels displayed in the plot as desired  The constructor for ConfusionMatrixDisplay doesn t provide a way to do much additional customization of the plot  but you can access the matplotlib axes obect via the ax  attribute after calling its plot   method  I ve added a second example showing this  I found it annoying to have to rerun a classifier over a large amount of data just to produce the plot with plot confusion matrix  I am producing other plots off the predicted data  so I don t want to waste my time re-predicting every time  This was an easy solution to that problem as well  Example  from sklearn metrics import confusion matrix  ConfusionMatrixDisplay  cm   confusion matrix y true  y preds  normalize  all   cmd   ConfusionMatrixDisplay cm  display labels   business   health    cmd plot     Example using ax   cm   confusion matrix y true  y preds  normalize  all   cmd   ConfusionMatrixDisplay cm  display labels   business   health    cmd plot   cmd ax  set xlabel  Predicted   ylabel  True

User · Answer

I found a function that can plot the confusion matrix which generated from sklearn   import numpy as np   def plot confusion matrix cm                            target names                            title  Confusion matrix                             cmap None                            normalize True               given a sklearn confusion matrix  cm   make a nice plot      Arguments     ---------     cm            confusion matrix from sklearn metrics confusion matrix      target names  given classification classes such as  0  1  2                    the class names  for example    high    medium    low        title         the text to display at the top of the matrix      cmap          the gradient of the values displayed from matplotlib pyplot cm                   see http   matplotlib org examples color colormaps reference html                   plt get cmap  jet   or plt cm Blues      normalize     If False  plot the raw numbers                   If True  plot the proportions      Usage     -----     plot confusion matrix cm             cm                     confusion matrix created by                                                                 sklearn metrics confusion matrix                           normalize      True                   show proportions                           target names   y labels vals          list of names of the classes                           title          best estimator name    title of graph      Citiation     ---------     http   scikit-learn org stable auto examples model selection plot confusion matrix html              import matplotlib pyplot as plt     import numpy as np     import itertools      accuracy   np trace cm    np sum cm  astype  float       misclass   1 - accuracy      if cmap is None          cmap   plt get cmap  Blues        plt figure figsize  8  6       plt imshow cm  interpolation  nearest   cmap cmap      plt title title      plt colorbar        if target names is not None          tick marks   np arange len target names           plt xticks tick marks  target names  rotation 45          plt yticks tick marks  target names       if normalize          cm   cm astype  float     cm sum axis 1     np newaxis        thresh   cm max     1 5 if normalize else cm max     2     for i  j in itertools product range cm shape 0    range cm shape 1             if normalize              plt text j  i     0 4f   format cm i  j                         horizontalalignment  center                        color  white  if cm i  j   gt  thresh else  black           else              plt text j  i         format cm i  j                         horizontalalignment  center                        color  white  if cm i  j   gt  thresh else  black         plt tight layout       plt ylabel  True label       plt xlabel  Predicted label naccuracy   0 4f   misclass   0 4f   format accuracy  misclass       plt show     It will look like this

User · Answer

from sklearn import model selection test size   0 33 seed   7 X train  X test  y train  y test   model selection train test split feature vectors  y  test size test size  random state seed   from sklearn metrics import accuracy score  f1 score  precision score  recall score  classification report  confusion matrix  model   LogisticRegression   model fit X train  y train  result   model score X test  y test  print  Accuracy    3f       result 100 0   y pred   model predict X test  print  F1 Score     f1 score y test  y pred  average  macro    print  Precision Score     precision score y test  y pred  average  macro    print  Recall Score     recall score y test  y pred  average  macro      import numpy as np import pandas as pd import matplotlib pyplot as plt import seaborn as sns from sklearn metrics import confusion matrix  def cm analysis y true  y pred  labels  ymap None  figsize  10 10                Generate matrix plot of confusion matrix with pretty annotations      The plot image is saved to disk      args         y true     true label of the data  with shape  nsamples         y pred     prediction of the data  with shape  nsamples         filename   filename of figure file to save       labels     string array  name the order of class labels in the confusion matrix                   use  clf classes   if using scikit-learn models                   with shape  nclass          ymap       dict  any - gt  string  length    nclass                   if not None  map the labels  amp  ys to more understandable strings                   Caution  original y true  y pred and labels must align        figsize    the size of the figure plotted              if ymap is not None          y pred    ymap yi  for yi in y pred          y true    ymap yi  for yi in y true          labels    ymap yi  for yi in labels      cm   confusion matrix y true  y pred  labels labels      cm sum   np sum cm  axis 1  keepdims True      cm perc   cm   cm sum astype float    100     annot   np empty like cm  astype str      nrows  ncols   cm shape     for i in range nrows           for j in range ncols               c   cm i  j              p   cm perc i  j              if i    j                  s   cm sum i                  annot i  j       1f   n d  d     p  c  s              elif c    0                  annot i  j                   else                  annot i  j       1f   n d     p  c      cm   pd DataFrame cm  index labels  columns labels      cm index name    Actual      cm columns name    Predicted      fig  ax   plt subplots figsize figsize      sns heatmap cm  annot annot  fmt     ax ax       plt savefig filename      plt show    cm analysis y test  y pred  model classes   ymap None  figsize  10 10       using https   gist github com hitvoice 36cf44689065ca9b927431546381a3f7  Note that if you use rocket r it will reverse the colors and somehow it looks more natural and better such as below

User · Answer

from sklearn metrics import confusion matrix     import seaborn as sns     import matplotlib pyplot as plt     model fit train x  train y validation split   0 1  epochs 50  batch size 4      y pred model predict test x batch size 15      cm  confusion matrix test y argmax axis 1   y pred argmax axis 1         index     neutral   happy   sad         columns     neutral   happy   sad         cm df   pd DataFrame cm columns index                            plt figure figsize  10 6         sns heatmap cm df  annot True

User · Answer

You might be interested by https   github com pandas-ml pandas-ml   which implements a Python Pandas implementation of Confusion Matrix   Some features    plot confusion matrix plot normalized confusion matrix class statistics overall statistics   Here is an example   In  1   from pandas ml import ConfusionMatrix In  2   import matplotlib pyplot as plt  In  3   y test     business    business    business    business    business            business    business    business    business    business            business    business    business    business    business            business    business    business    business    business    In  4   y pred     health    business    business    business    business           business    health    health    business    business    business           business    business    business    business    business           health    health    business    health    In  5   cm   ConfusionMatrix y test  y pred   In  6   cm Out 6   Predicted  business  health    all   Actual business         14       6       20 health            0       0        0   all            14       6       20  In  7   cm plot   Out 7    lt matplotlib axes  subplots AxesSubplot at 0x1093cf9b0 gt   In  8   plt show       In  9   cm print stats   Confusion Matrix   Predicted  business  health    all   Actual business         14       6       20 health            0       0        0   all            14       6       20   Overall Statistics   Accuracy  0 7 95  CI   0 45721081772371086  0 88106840959427235  No Information Rate  ToDo P-Value  Acc  gt  NIR   0 608009812201 Kappa  0 0 Mcnemar s Test P-Value  ToDo   Class Statistics   Classes                                 business health Population                                    20     20 P  Condition positive                         20      0 N  Condition negative                          0     20 Test outcome positive                         14      6 Test outcome negative                          6     14 TP  True Positive                             14      0 TN  True Negative                              0     14 FP  False Positive                             0      6 FN  False Negative                             6      0 TPR   Sensitivity  hit rate  recall          0 7    NaN TNR SPC   Specificity                        NaN    0 7 PPV  Pos Pred Value  Precision                 1      0 NPV  Neg Pred Value                            0      1 FPR  False-out                               NaN    0 3 FDR  False Discovery Rate                      0      1 FNR  Miss Rate                               0 3    NaN ACC  Accuracy                                0 7    0 7 F1 score                               0 8235294      0 MCC  Matthews correlation coefficient        NaN    NaN Informedness                                 NaN    NaN Markedness                                     0      0 Prevalence                                     1      0 LR   Positive likelihood ratio               NaN    NaN LR-  Negative likelihood ratio               NaN    NaN DOR  Diagnostic odds ratio                   NaN    NaN FOR  False omission rate                       1      0

[python] sklearn plot confusion matrix with labels

Examples related to python

Examples related to matplotlib

Examples related to scikit-learn