Mixing
Is there a way to plot the two different sources into same graph using MatplotLib?
I am creating clusters of top 10 most common words, and my filter_data has the set of word token list. I am able to plot the clusters of those 10 words after vectorizing but after comparing the lemmas of the most common words with filter data I want to plot the word token list in the same graph. So that all the words get plotted into their own relevant clusters. How should I do that?
I have tried vectorizing the data of most common words as well as the whole token list. Moreover, the top 10 most common words are being extracted out of the filter_data token list. In simple words I am trying to plot the semantic clusters using matplotlib.
import string
import re
import nltk
import PyPDF4
import numpy
from collections import Counter
from sklearn.cluster import KMeans
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.decomposition import PCA
from nltk.corpus import wordnet
import matplotlib.pyplot as plt
# Declaring all the variables
stopwords = nltk.corpus.stopwords.words('english')
# additional stopwords to be removed manually.
file = open('Corpus.txt', 'r')
moreStopwords = file.read().splitlines()
ps = nltk.PorterStemmer()
wn = nltk.WordNetLemmatizer()
data = PyPDF4.PdfFileReader(open('ReadyPlayerOne.pdf', 'rb'))
pageData = ''
for page in data.pages:
pageData += page.extractText()
def clean_text(text):
text = "".join([word.lower() for word in text if word not in
string.punctuation])
tokenize = re.split("W+", text)
text = [wn.lemmatize(word) for word in tokenize if word not in stopwords]
final = [word for word in text if word not in moreStopwords]
return final
filter_data = clean_text(pageData)
# get most common words & plot them on bar graph
most_common_words = [word for word, word_count in
Counter(filter_data).most_common(10)]
word_freq = [word_count for word, word_count in
Counter(filter_data).most_common(10)
mcw_lemma =
for token in most_common_words:
synsets = wordnet.synsets(token)
if synsets:
mcw_lemma.append(synsets[0].lemmas()[0].name())
fd_lemma =
for token in filter_data:
synsets = wordnet.synsets(token)
if synsets:
fd_lemma.append(synsets[0].lemmas()[0].name())
# Vectorizing most common words & filter data
mcw_vec = TfidfVectorizer(analyzer=clean_text)
fd_vec = TfidfVectorizer(analyzer=clean_text)
tfidf_mcw = mcw_vec.fit_transform(mcw_lemma)
tfidf_fd = fd_vec.fit_transform(fd_lemma)
# Create cluster
cluster = KMeans(n_clusters=len(mcw_lemma), max_iter=300,
precompute_distances='auto', n_jobs=-1)
X = cluster.fit_transform(tfidf_mcw)
pca = PCA(n_components=2).fit(X)
data2D = pca.transform(X)
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(mcw_lemma)))
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(fd_lemma)))
plt.show()
Suppose the most common words are:
['one', 'oasis', 'halliday', 'avatar', 'time', 'school', 'year', 'thing', 'old', 'stack']
They will be plotted in the graph and they should have their own clusters where the other words are plotted sharing the same lemma.
python matplotlib wordnet
asked Jan 2 at 21:17
TonyTony
167
add a comment |
I am creating clusters of top 10 most common words, and my filter_data has the set of word token list. I am able to plot the clusters of those 10 words after vectorizing but after comparing the lemmas of the most common words with filter data I want to plot the word token list in the same graph. So that all the words get plotted into their own relevant clusters. How should I do that?
I have tried vectorizing the data of most common words as well as the whole token list. Moreover, the top 10 most common words are being extracted out of the filter_data token list. In simple words I am trying to plot the semantic clusters using matplotlib.
import string
import re
import nltk
import PyPDF4
import numpy
from collections import Counter
from sklearn.cluster import KMeans
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.decomposition import PCA
from nltk.corpus import wordnet
import matplotlib.pyplot as plt
# Declaring all the variables
stopwords = nltk.corpus.stopwords.words('english')
# additional stopwords to be removed manually.
file = open('Corpus.txt', 'r')
moreStopwords = file.read().splitlines()
ps = nltk.PorterStemmer()
wn = nltk.WordNetLemmatizer()
data = PyPDF4.PdfFileReader(open('ReadyPlayerOne.pdf', 'rb'))
pageData = ''
for page in data.pages:
pageData += page.extractText()
def clean_text(text):
text = "".join([word.lower() for word in text if word not in
string.punctuation])
tokenize = re.split("W+", text)
text = [wn.lemmatize(word) for word in tokenize if word not in stopwords]
final = [word for word in text if word not in moreStopwords]
return final
filter_data = clean_text(pageData)
# get most common words & plot them on bar graph
most_common_words = [word for word, word_count in
Counter(filter_data).most_common(10)]
word_freq = [word_count for word, word_count in
Counter(filter_data).most_common(10)
mcw_lemma =
for token in most_common_words:
synsets = wordnet.synsets(token)
if synsets:
mcw_lemma.append(synsets[0].lemmas()[0].name())
fd_lemma =
for token in filter_data:
synsets = wordnet.synsets(token)
if synsets:
fd_lemma.append(synsets[0].lemmas()[0].name())
# Vectorizing most common words & filter data
mcw_vec = TfidfVectorizer(analyzer=clean_text)
fd_vec = TfidfVectorizer(analyzer=clean_text)
tfidf_mcw = mcw_vec.fit_transform(mcw_lemma)
tfidf_fd = fd_vec.fit_transform(fd_lemma)
# Create cluster
cluster = KMeans(n_clusters=len(mcw_lemma), max_iter=300,
precompute_distances='auto', n_jobs=-1)
X = cluster.fit_transform(tfidf_mcw)
pca = PCA(n_components=2).fit(X)
data2D = pca.transform(X)
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(mcw_lemma)))
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(fd_lemma)))
plt.show()
Suppose the most common words are:
['one', 'oasis', 'halliday', 'avatar', 'time', 'school', 'year', 'thing', 'old', 'stack']
They will be plotted in the graph and they should have their own clusters where the other words are plotted sharing the same lemma.
python matplotlib wordnet
asked Jan 2 at 21:17
TonyTony
167
add a comment |
I am creating clusters of top 10 most common words, and my filter_data has the set of word token list. I am able to plot the clusters of those 10 words after vectorizing but after comparing the lemmas of the most common words with filter data I want to plot the word token list in the same graph. So that all the words get plotted into their own relevant clusters. How should I do that?
I have tried vectorizing the data of most common words as well as the whole token list. Moreover, the top 10 most common words are being extracted out of the filter_data token list. In simple words I am trying to plot the semantic clusters using matplotlib.
import string
import re
import nltk
import PyPDF4
import numpy
from collections import Counter
from sklearn.cluster import KMeans
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.decomposition import PCA
from nltk.corpus import wordnet
import matplotlib.pyplot as plt
# Declaring all the variables
stopwords = nltk.corpus.stopwords.words('english')
# additional stopwords to be removed manually.
file = open('Corpus.txt', 'r')
moreStopwords = file.read().splitlines()
ps = nltk.PorterStemmer()
wn = nltk.WordNetLemmatizer()
data = PyPDF4.PdfFileReader(open('ReadyPlayerOne.pdf', 'rb'))
pageData = ''
for page in data.pages:
pageData += page.extractText()
def clean_text(text):
text = "".join([word.lower() for word in text if word not in
string.punctuation])
tokenize = re.split("W+", text)
text = [wn.lemmatize(word) for word in tokenize if word not in stopwords]
final = [word for word in text if word not in moreStopwords]
return final
filter_data = clean_text(pageData)
# get most common words & plot them on bar graph
most_common_words = [word for word, word_count in
Counter(filter_data).most_common(10)]
word_freq = [word_count for word, word_count in
Counter(filter_data).most_common(10)
mcw_lemma =
for token in most_common_words:
synsets = wordnet.synsets(token)
if synsets:
mcw_lemma.append(synsets[0].lemmas()[0].name())
fd_lemma =
for token in filter_data:
synsets = wordnet.synsets(token)
if synsets:
fd_lemma.append(synsets[0].lemmas()[0].name())
# Vectorizing most common words & filter data
mcw_vec = TfidfVectorizer(analyzer=clean_text)
fd_vec = TfidfVectorizer(analyzer=clean_text)
tfidf_mcw = mcw_vec.fit_transform(mcw_lemma)
tfidf_fd = fd_vec.fit_transform(fd_lemma)
# Create cluster
cluster = KMeans(n_clusters=len(mcw_lemma), max_iter=300,
precompute_distances='auto', n_jobs=-1)
X = cluster.fit_transform(tfidf_mcw)
pca = PCA(n_components=2).fit(X)
data2D = pca.transform(X)
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(mcw_lemma)))
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(fd_lemma)))
plt.show()
Suppose the most common words are:
['one', 'oasis', 'halliday', 'avatar', 'time', 'school', 'year', 'thing', 'old', 'stack']
They will be plotted in the graph and they should have their own clusters where the other words are plotted sharing the same lemma.
python matplotlib wordnet
asked Jan 2 at 21:17
TonyTony
167
I am creating clusters of top 10 most common words, and my filter_data has the set of word token list. I am able to plot the clusters of those 10 words after vectorizing but after comparing the lemmas of the most common words with filter data I want to plot the word token list in the same graph. So that all the words get plotted into their own relevant clusters. How should I do that?
I have tried vectorizing the data of most common words as well as the whole token list. Moreover, the top 10 most common words are being extracted out of the filter_data token list. In simple words I am trying to plot the semantic clusters using matplotlib.
import string
import re
import nltk
import PyPDF4
import numpy
from collections import Counter
from sklearn.cluster import KMeans
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.decomposition import PCA
from nltk.corpus import wordnet
import matplotlib.pyplot as plt
# Declaring all the variables
stopwords = nltk.corpus.stopwords.words('english')
# additional stopwords to be removed manually.
file = open('Corpus.txt', 'r')
moreStopwords = file.read().splitlines()
ps = nltk.PorterStemmer()
wn = nltk.WordNetLemmatizer()
data = PyPDF4.PdfFileReader(open('ReadyPlayerOne.pdf', 'rb'))
pageData = ''
for page in data.pages:
pageData += page.extractText()
def clean_text(text):
text = "".join([word.lower() for word in text if word not in
string.punctuation])
tokenize = re.split("W+", text)
text = [wn.lemmatize(word) for word in tokenize if word not in stopwords]
final = [word for word in text if word not in moreStopwords]
return final
filter_data = clean_text(pageData)
# get most common words & plot them on bar graph
most_common_words = [word for word, word_count in
Counter(filter_data).most_common(10)]
word_freq = [word_count for word, word_count in
Counter(filter_data).most_common(10)
mcw_lemma =
for token in most_common_words:
synsets = wordnet.synsets(token)
if synsets:
mcw_lemma.append(synsets[0].lemmas()[0].name())
fd_lemma =
for token in filter_data:
synsets = wordnet.synsets(token)
if synsets:
fd_lemma.append(synsets[0].lemmas()[0].name())
# Vectorizing most common words & filter data
mcw_vec = TfidfVectorizer(analyzer=clean_text)
fd_vec = TfidfVectorizer(analyzer=clean_text)
tfidf_mcw = mcw_vec.fit_transform(mcw_lemma)
tfidf_fd = fd_vec.fit_transform(fd_lemma)
# Create cluster
cluster = KMeans(n_clusters=len(mcw_lemma), max_iter=300,
precompute_distances='auto', n_jobs=-1)
X = cluster.fit_transform(tfidf_mcw)
pca = PCA(n_components=2).fit(X)
data2D = pca.transform(X)
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(mcw_lemma)))
plt.scatter(data2D[:, 0], data2D[:, 0],
c=numpy.random.random(len(fd_lemma)))
plt.show()
Suppose the most common words are:
['one', 'oasis', 'halliday', 'avatar', 'time', 'school', 'year', 'thing', 'old', 'stack']
They will be plotted in the graph and they should have their own clusters where the other words are plotted sharing the same lemma.
python matplotlib wordnet
python matplotlib wordnet
asked Jan 2 at 21:17
TonyTony
167
asked Jan 2 at 21:17
TonyTony
167
asked Jan 2 at 21:17
TonyTony
167
asked Jan 2 at 21:17
TonyTony
167
asked Jan 2 at 21:17
TonyTony
167
167
add a comment |
add a comment |
0
active
oldest
votes
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54013309%2fis-there-a-way-to-plot-the-two-different-sources-into-same-graph-using-matplotli%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54013309%2fis-there-a-way-to-plot-the-two-different-sources-into-same-graph-using-matplotli%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
