In [1]:

    

run document_classification_20newsgroups1.py


    

    




======================================================
Classification of text documents using sparse features
======================================================

This is an example showing how scikit-learn can be used to classify documents
by topics using a bag-of-words approach. This example uses a scipy.sparse
matrix to store the features and demonstrates various classifiers that can
efficiently handle sparse matrices.

The dataset used in this example is the 20 newsgroups dataset. It will be
automatically downloaded, then cached.

The bar plot indicates the accuracy, training time (normalized) and test time
(normalized) of each classifier.


Usage: document_classification_20newsgroups1.py [options]

Options:
  -h, --help            show this help message and exit
  --report              Print a detailed classification report.
  --chi2_select=SELECT_CHI2
                        Select some number of features using a chi-squared
                        test
  --confusion_matrix    Print the confusion matrix.
  --top10               Print ten most discriminative terms per class for
                        every classifier.
  --all_categories      Whether to use all categories or not.
  --use_hashing         Use a hashing vectorizer.
  --n_features=N_FEATURES
                        n_features when using the hashing vectorizer.
  --filtered            Remove newsgroup information that is easily overfit:
                        headers, signatures, and quoting.

Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
data loaded
2034 documents - 3.980MB (training set)
1353 documents - 2.867MB (test set)
4 categories

Extracting features from the training dataset using a sparse vectorizer
done in 0.773461s at 5.145MB/s
n_samples: 2034, n_features: 33810

Extracting features from the test dataset using the same vectorizer
done in 0.415789s at 6.897MB/s
n_samples: 1353, n_features: 33810

================================================================================
Ridge Classifier
________________________________________________________________________________
Training: 
RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
        max_iter=None, normalize=False, solver='lsqr', tol=0.01)
train time: 0.069s
test time:  0.002s
f1-score:   0.903
dimensionality: 33810
density: 1.000000


================================================================================
Perceptron
________________________________________________________________________________
Training: 
Perceptron(alpha=0.0001, class_weight=None, eta0=1.0, fit_intercept=True,
      n_iter=50, n_jobs=1, penalty=None, random_state=0, shuffle=True,
      verbose=0, warm_start=False)
train time: 0.100s





    




/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)






    




test time:  0.002s
f1-score:   0.884
dimensionality: 33810
density: 0.240158


================================================================================
Passive-Aggressive
________________________________________________________________________________
Training: 
PassiveAggressiveClassifier(C=1.0, fit_intercept=True, loss='hinge',
              n_iter=50, n_jobs=1, random_state=None, shuffle=True,
              verbose=0, warm_start=False)
train time: 0.134s
test time:  0.003s
f1-score:   0.900
dimensionality: 33810
density: 0.699919


================================================================================
kNN
________________________________________________________________________________
Training: 
KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_neighbors=10, p=2, weights='uniform')
train time: 0.001s
test time:  0.214s





    




/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)






    




f1-score:   0.856

================================================================================
L2 penalty
________________________________________________________________________________
Training: 
LinearSVC(C=1.0, class_weight=None, dual=False, fit_intercept=True,
     intercept_scaling=1, loss='l2', max_iter=1000, multi_class='ovr',
     penalty='l2', random_state=None, tol=0.001, verbose=0)
train time: 0.137s





    




/Applications/anaconda/lib/python2.7/site-packages/sklearn/svm/classes.py:192: DeprecationWarning: loss='l2' has been deprecated in favor of loss='squared_hinge' as of 0.16. Backward compatibility for the loss='l2' will be removed in 1.0
  DeprecationWarning)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)






    




test time:  0.004s
f1-score:   0.899
dimensionality: 33810
density: 1.000000


________________________________________________________________________________
Training: 
SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
       eta0=0.0, fit_intercept=True, l1_ratio=0.15,
       learning_rate='optimal', loss='hinge', n_iter=50, n_jobs=1,
       penalty='l2', power_t=0.5, random_state=None, shuffle=True,
       verbose=0, warm_start=False)
train time: 0.153s
test time:  0.002s
f1-score:   0.903
dimensionality: 33810
density: 0.667606


================================================================================
L1 penalty
________________________________________________________________________________
Training: 
LinearSVC(C=1.0, class_weight=None, dual=False, fit_intercept=True,
     intercept_scaling=1, loss='l2', max_iter=1000, multi_class='ovr',
     penalty='l1', random_state=None, tol=0.001, verbose=0)
train time: 0.207s





    




/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/svm/classes.py:192: DeprecationWarning: loss='l2' has been deprecated in favor of loss='squared_hinge' as of 0.16. Backward compatibility for the loss='l2' will be removed in 1.0
  DeprecationWarning)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)






    




test time:  0.001s
f1-score:   0.871
dimensionality: 33810
density: 0.005538


________________________________________________________________________________
Training: 
SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
       eta0=0.0, fit_intercept=True, l1_ratio=0.15,
       learning_rate='optimal', loss='hinge', n_iter=50, n_jobs=1,
       penalty='l1', power_t=0.5, random_state=None, shuffle=True,
       verbose=0, warm_start=False)
train time: 0.446s
test time:  0.002s
f1-score:   0.884
dimensionality: 33810
density: 0.020016


================================================================================
Elastic-Net penalty
________________________________________________________________________________
Training: 
SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
       eta0=0.0, fit_intercept=True, l1_ratio=0.15,
       learning_rate='optimal', loss='hinge', n_iter=50, n_jobs=1,
       penalty='elasticnet', power_t=0.5, random_state=None, shuffle=True,
       verbose=0, warm_start=False)
train time: 0.610s





    




/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)






    




test time:  0.004s
f1-score:   0.899
dimensionality: 33810
density: 0.188827


================================================================================
NearestCentroid (aka Rocchio classifier)
________________________________________________________________________________
Training: 
NearestCentroid(metric='euclidean', shrink_threshold=None)
train time: 0.033s
test time:  0.005s
f1-score:   0.853

================================================================================
Naive Bayes
________________________________________________________________________________
Training: 
MultinomialNB(alpha=0.01, class_prior=None, fit_prior=True)
train time: 0.006s
test time:  0.002s
f1-score:   0.899
dimensionality: 33810
density: 1.000000


________________________________________________________________________________
Training: 
BernoulliNB(alpha=0.01, binarize=0.0, class_prior=None, fit_prior=True)
train time: 0.010s
test time:  0.009s
f1-score:   0.883
dimensionality: 33810
density: 1.000000


================================================================================
LinearSVC with L1-based feature selection
________________________________________________________________________________
Training: 
L1LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,
      intercept_scaling=1, loss='squared_hinge', max_iter=1000,
      multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,
      verbose=0)
train time: 0.240s





    




/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)
/Applications/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.py:676: DeprecationWarning: The default `weighted` averaging is deprecated, and from version 0.18, use of precision, recall or F-score with multiclass or multilabel data or pos_label=None will result in an exception. Please set an explicit value for `average`, one of (None, 'micro', 'macro', 'weighted', 'samples'). In cross validation use, for instance, scoring="f1_weighted" instead of scoring="f1".
  sample_weight=sample_weight)






    




test time:  0.006s
f1-score:   0.879
dimensionality: 561
density: 0.999554

In [4]:

    

# %load document_classification_20newsgroups1.py
"""
======================================================
Classification of text documents using sparse features
======================================================

This is an example showing how scikit-learn can be used to classify documents
by topics using a bag-of-words approach. This example uses a scipy.sparse
matrix to store the features and demonstrates various classifiers that can
efficiently handle sparse matrices.

The dataset used in this example is the 20 newsgroups dataset. It will be
automatically downloaded, then cached.

The bar plot indicates the accuracy, training time (normalized) and test time
(normalized) of each classifier.

"""

# Author: Peter Prettenhofer <peter.prettenhofer@gmail.com>
#         Olivier Grisel <olivier.grisel@ensta.org>
#         Mathieu Blondel <mathieu@mblondel.org>
#         Lars Buitinck <L.J.Buitinck@uva.nl>
# License: BSD 3 clause

from __future__ import print_function

import logging
import numpy as np
from optparse import OptionParser
import sys
from time import time
import matplotlib.pyplot as plt

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.linear_model import RidgeClassifier
from sklearn.svm import LinearSVC
from sklearn.linear_model import SGDClassifier
from sklearn.linear_model import Perceptron
from sklearn.linear_model import PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB, MultinomialNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors import NearestCentroid
from sklearn.utils.extmath import density
from sklearn import metrics


    

In [6]:

    

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s %(levelname)s %(message)s')


# parse commandline arguments
op = OptionParser()
op.add_option("--report",
              action="store_true", dest="print_report",
              help="Print a detailed classification report.")
op.add_option("--chi2_select",
              action="store", type="int", dest="select_chi2",
              help="Select some number of features using a chi-squared test")
op.add_option("--confusion_matrix",
              action="store_true", dest="print_cm",
              help="Print the confusion matrix.")
op.add_option("--top10",
              action="store_true", dest="print_top10",
              help="Print ten most discriminative terms per class"
                   " for every classifier.")
op.add_option("--all_categories",
              action="store_true", dest="all_categories",
              help="Whether to use all categories or not.")
op.add_option("--use_hashing",
              action="store_true",
              help="Use a hashing vectorizer.")
op.add_option("--n_features",
              action="store", type=int, default=2 ** 16,
              help="n_features when using the hashing vectorizer.")
op.add_option("--filtered",
              action="store_true",
              help="Remove newsgroup information that is easily overfit: "
                   "headers, signatures, and quoting.")


    

    
Out[6]:





<Option at 0x10c1aab48: --filtered>

In [8]:

    

# (opts, args) = op.parse_args()
# if len(args) > 0:
#     op.error("this script takes no arguments.")
#     sys.exit(1)

# print(__doc__)
# op.print_help()
# print()


    

In [9]:

    

###############################################################################
# Load some categories from the training set
if opts.all_categories:
    categories = None
else:
    categories = [
        'alt.atheism',
        'talk.religion.misc',
        'comp.graphics',
        'sci.space',
    ]


    

In [10]:

    

categories


    

    
Out[10]:





['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']

In [11]:

    

if opts.filtered:
    remove = ('headers', 'footers', 'quotes')
else:
    remove = ()

print("Loading 20 newsgroups dataset for categories:")
print(categories if categories else "all")

data_train = fetch_20newsgroups(subset='train', categories=categories,
                                shuffle=True, random_state=42,
                                remove=remove)

data_test = fetch_20newsgroups(subset='test', categories=categories,
                               shuffle=True, random_state=42,
                               remove=remove)
print('data loaded')

categories = data_train.target_names    # for case categories == None


def size_mb(docs):
    return sum(len(s.encode('utf-8')) for s in docs) / 1e6

data_train_size_mb = size_mb(data_train.data)
data_test_size_mb = size_mb(data_test.data)

print("%d documents - %0.3fMB (training set)" % (
    len(data_train.data), data_train_size_mb))
print("%d documents - %0.3fMB (test set)" % (
    len(data_test.data), data_test_size_mb))
print("%d categories" % len(categories))
print()

# split a training set and a test set
y_train, y_test = data_train.target, data_test.target


    

    




Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
data loaded
2034 documents - 3.980MB (training set)
1353 documents - 2.867MB (test set)
4 categories

In [17]:

    

train_data = data_train.data


    

In [18]:

    

train_data[0]


    

    
Out[18]:





u"From: rych@festival.ed.ac.uk (R Hawkes)\nSubject: 3DS: Where did all the texture rules go?\nLines: 21\n\nHi,\n\nI've noticed that if you only save a model (with all your mapping planes\npositioned carefully) to a .3DS file that when you reload it after restarting\n3DS, they are given a default position and orientation.  But if you save\nto a .PRJ file their positions/orientation are preserved.  Does anyone\nknow why this information is not stored in the .3DS file?  Nothing is\nexplicitly said in the manual about saving texture rules in the .PRJ file. \nI'd like to be able to read the texture rule information, does anyone have \nthe format for the .PRJ file?\n\nIs the .CEL file format available from somewhere?\n\nRych\n\n======================================================================\nRycharde Hawkes\t\t\t\temail: rych@festival.ed.ac.uk\nVirtual Environment Laboratory\nDept. of Psychology\t\t\tTel  : +44 31 650 3426\nUniv. of Edinburgh\t\t\tFax  : +44 31 667 0150\n======================================================================\n"

In [ ]:

    

print("Extracting features from the training dataset using a sparse vectorizer")
t0 = time()
if opts.use_hashing:
    vectorizer = HashingVectorizer(stop_words='english', non_negative=True,
                                   n_features=opts.n_features)
    X_train = vectorizer.transform(data_train.data)
else:
    vectorizer = TfidfVectorizer(sublinear_tf=True, max_df=0.5,
                                 stop_words='english')
    X_train = vectorizer.fit_transform(data_train.data)
duration = time() - t0
print("done in %fs at %0.3fMB/s" % (duration, data_train_size_mb / duration))
print("n_samples: %d, n_features: %d" % X_train.shape)
print()

print("Extracting features from the test dataset using the same vectorizer")
t0 = time()
X_test = vectorizer.transform(data_test.data)
duration = time() - t0
print("done in %fs at %0.3fMB/s" % (duration, data_test_size_mb / duration))
print("n_samples: %d, n_features: %d" % X_test.shape)
print()

if opts.select_chi2:
    print("Extracting %d best features by a chi-squared test" %
          opts.select_chi2)
    t0 = time()
    ch2 = SelectKBest(chi2, k=opts.select_chi2)
    X_train = ch2.fit_transform(X_train, y_train)
    X_test = ch2.transform(X_test)
    print("done in %fs" % (time() - t0))
    print()


def trim(s):
    """Trim string to fit on terminal (assuming 80-column display)"""
    return s if len(s) <= 80 else s[:77] + "..."


# mapping from integer feature name to original token string
if opts.use_hashing:
    feature_names = None
else:
    feature_names = np.asarray(vectorizer.get_feature_names())


###############################################################################
# Benchmark classifiers
def benchmark(clf):
    print('_' * 80)
    print("Training: ")
    print(clf)
    t0 = time()
    clf.fit(X_train, y_train)
    train_time = time() - t0
    print("train time: %0.3fs" % train_time)

    t0 = time()
    pred = clf.predict(X_test)
    test_time = time() - t0
    print("test time:  %0.3fs" % test_time)

    score = metrics.f1_score(y_test, pred)
    print("f1-score:   %0.3f" % score)

    if hasattr(clf, 'coef_'):
        print("dimensionality: %d" % clf.coef_.shape[1])
        print("density: %f" % density(clf.coef_))

        if opts.print_top10 and feature_names is not None:
            print("top 10 keywords per class:")
            for i, category in enumerate(categories):
                top10 = np.argsort(clf.coef_[i])[-10:]
                print(trim("%s: %s"
                      % (category, " ".join(feature_names[top10]))))
        print()

    if opts.print_report:
        print("classification report:")
        print(metrics.classification_report(y_test, pred,
                                            target_names=categories))

    if opts.print_cm:
        print("confusion matrix:")
        print(metrics.confusion_matrix(y_test, pred))

    print()
    clf_descr = str(clf).split('(')[0]
    return clf_descr, score, train_time, test_time


results = []
for clf, name in (
        (RidgeClassifier(tol=1e-2, solver="lsqr"), "Ridge Classifier"),
        (Perceptron(n_iter=50), "Perceptron"),
        (PassiveAggressiveClassifier(n_iter=50), "Passive-Aggressive"),
        (KNeighborsClassifier(n_neighbors=10), "kNN")):
    print('=' * 80)
    print(name)
    results.append(benchmark(clf))

for penalty in ["l2", "l1"]:
    print('=' * 80)
    print("%s penalty" % penalty.upper())
    # Train Liblinear model
    results.append(benchmark(LinearSVC(loss='l2', penalty=penalty,
                                            dual=False, tol=1e-3)))

    # Train SGD model
    results.append(benchmark(SGDClassifier(alpha=.0001, n_iter=50,
                                           penalty=penalty)))

# Train SGD with Elastic Net penalty
print('=' * 80)
print("Elastic-Net penalty")
results.append(benchmark(SGDClassifier(alpha=.0001, n_iter=50,
                                       penalty="elasticnet")))

# Train NearestCentroid without threshold
print('=' * 80)
print("NearestCentroid (aka Rocchio classifier)")
results.append(benchmark(NearestCentroid()))

# Train sparse Naive Bayes classifiers
print('=' * 80)
print("Naive Bayes")
results.append(benchmark(MultinomialNB(alpha=.01)))
results.append(benchmark(BernoulliNB(alpha=.01)))


class L1LinearSVC(LinearSVC):

    def fit(self, X, y):
        # The smaller C, the stronger the regularization.
        # The more regularization, the more sparsity.
        self.transformer_ = LinearSVC(penalty="l1",
                                      dual=False, tol=1e-3)
        X = self.transformer_.fit_transform(X, y)
        return LinearSVC.fit(self, X, y)

    def predict(self, X):
        X = self.transformer_.transform(X)
        return LinearSVC.predict(self, X)

print('=' * 80)
print("LinearSVC with L1-based feature selection")
results.append(benchmark(L1LinearSVC()))


# make some plots

indices = np.arange(len(results))

results = [[x[i] for x in results] for i in range(4)]

clf_names, score, training_time, test_time = results
training_time = np.array(training_time) / np.max(training_time)
test_time = np.array(test_time) / np.max(test_time)

plt.figure(figsize=(12, 8))
plt.title("Score")
plt.barh(indices, score, .2, label="score", color='r')
plt.barh(indices + .3, training_time, .2, label="training time", color='g')
plt.barh(indices + .6, test_time, .2, label="test time", color='b')
plt.yticks(())
plt.legend(loc='best')
plt.subplots_adjust(left=.25)
plt.subplots_adjust(top=.95)
plt.subplots_adjust(bottom=.05)

for i, c in zip(indices, clf_names):
    plt.text(-.3, i, c)

plt.show()


    

In [ ]: