I have to preprocess NLP data, so I've to remove the stopwords (from nltk library) from a Tensorflow dataset. I tried many thing like this:
docs = tf.data.Dataset.from_tensor_slices([['Never tell me the odds.'], ["It's a trap!"]])
tokenizer = text.WhitespaceTokenizer()
tokenized_docs = docs.map(lambda x: tokenizer.tokenize(x))
data = tokenized_docs.filter(lambda x: x. not in stop_words)
or this:
tokens = docs.map(lambda x: tokenizer.tokenize(x))
data = tokens.filter(lambda x: tf.strings.strip(x).ref() not in stopwords)
But it didn't work. This first code shows an error like: RaggedTensor is unhashable.
From what I can tell Tensorflow supports basic string normalization (lowercasing + punctuation stripping) using the standardize callback's standardization function. There doesn't appear to be support for more advanced options, like removing stop words without doing it yourself.
It's probably easier to just do the standardization beforehand, outside of TensorFlow and then pass the result on.
import re
import nltk
from nltk.corpus import stopwords
nltk.download('stopwords')
def parse_text(text):
print(f'Input: {text}')
text = re.sub("[^a-zA-Z]", ' ', text)
print(f'Remove punctuation and numbers: {text}')
text = text.lower().split()
print(f'Lowercase and split: {text}')
swords = set(stopwords.words("english"))
text = [w for w in text if w not in swords]
print(f'Remove stop words: {text}')
text = " ".join(text)
print(f'Final: {text}')
return text
list1 = [["NEver tell me the odds."],["It's a trap!"]]
for sublist in list1:
for i in range(len(sublist)):
sublist[i] = parse_text(sublist[i])
print(list1)
# [['never tell odds'], ['trap']]
You can use this to remove stopwords when using tfx
from nltk.corpus import stopwords
outputs['review'] = tf.strings.regex_replace(inputs['review'], r'\b(' + r'|'.join(stopwords.words('english')) + r')\b\s*',"")
I have a pandas dataframe as follows.
thi 0.969378
text 0.969378
is 0.969378
anoth 0.699030
your 0.497120
first 0.497120
book 0.497120
third 0.445149
the 0.445149
for 0.445149
analysi 0.445149
I want to convert it to a list of tuples as follows.
[["this", 0.969378], ["text", 0.969378], ..., ["analysi", 0.445149]]
My code is as follows.
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from nltk import word_tokenize
from nltk.stem.porter import PorterStemmer
def tokenize(text):
tokens = word_tokenize(text)
stems = []
for item in tokens: stems.append(PorterStemmer().stem(item))
return stems
# your corpus
text = ["This is your first text book", "This is the third text for analysis", "This is another text"]
# word tokenize and stem
text = [" ".join(tokenize(txt.lower())) for txt in text]
vectorizer = TfidfVectorizer()
matrix = vectorizer.fit_transform(text).todense()
# transform the matrix to a pandas df
matrix = pd.DataFrame(matrix, columns=vectorizer.get_feature_names())
# sum over each document (axis=0)
top_words = matrix.sum(axis=0).sort_values(ascending=False)
print(top_words)
I tried the following two options.
list(zip(*map(top_words.get, top_words)))
I got the error as TypeError: cannot do label indexing on <class 'pandas.core.indexes.base.Index'> with these indexers [0.9693779251346359] of <class 'float'>
list(top_words.itertuples(index=True))
I got the error as AttributeError: 'Series' object has no attribute 'itertuples'.
Please let me know a quick way of doing this in pandas.
I am happy to provide more details if needed.
Use zip by index with map tuples to lists:
a = list(map(list,zip(top_words.index,top_words)))
Or convert index to column, convert to nupy array and then to lists:
a = top_words.reset_index().to_numpy().tolist()
print (a)
[['thi', 0.9693780000000001], ['text', 0.9693780000000001],
['is', 0.9693780000000001], ['anoth', 0.69903],
['your', 0.49712], ['first', 0.49712], ['book', 0.49712],
['third', 0.44514899999999996], ['the', 0.44514899999999996],
['for', 0.44514899999999996], ['analysi', 0.44514899999999996]]
Can't find module 'textacy' has no attribute 'Doc'
I am trying to extract verb phrases from spacy but there is such no library. Please help me how can I extract the verb phrases or adjective phrases using spacy. I want to do full shallow parsing.
def extract_named_nouns(row_series):
"""Combine nouns and non-numerical entities.
Keyword arguments:
row_series -- a Pandas Series object
"""
ents = set()
idxs = set()
# remove duplicates and merge two lists together
for noun_tuple in row_series['nouns']:
for named_ents_tuple in row_series['named_ents']:
if noun_tuple[1] == named_ents_tuple[1]:
idxs.add(noun_tuple[1])
ents.add(named_ents_tuple)
if noun_tuple[1] not in idxs:
ents.add(noun_tuple)
return sorted(list(ents), key=lambda x: x[1])
def add_named_nouns(df):
"""Create new column in data frame with nouns and named ents.
Keyword arguments:
df -- a dataframe object
"""
df['named_nouns'] = df.apply(extract_named_nouns, axis=1)
from __future__ import unicode_literals
import spacy,en_core_web_sm
import textacy
from textacy import io
#using spacy for nlp
nlp = en_core_web_sm.load()
sentence = 'The author is writing a new book.'
pattern = r'<VERB>?<ADV>*<VERB>+'
doc = textacy.Doc.load(sentence, metadata=metadata, lang='en_core_web_sm')
# doc = textacy.corpus.Corpus(sentence, lang='en_core_web_sm')
lists = textacy.extract.pos_regex_matches(doc, pattern)
for list in lists:
print(list.text)
module 'textacy' has no attribute 'Doc'
Try following the examples here: https://chartbeat-labs.github.io/textacy/getting_started/quickstart.html#make-a-doc
It should be as simple as:
doc = textacy.make_spacy_doc("The author is writing a new book.", lang='en_core_web_sm')
You might look into just using spacy (without textacy) with its built-in Matcher instead (https://spacy.io/usage/rule-based-matching).
spacy_lang = textacy.load_spacy_lang("en_core_web_en")
docx_textacy = spacy_lang(sentence)
I am using NLTK on a dataset stored as a pandas dataframe. All the raw text processing procedures worked fine until I tried to convert the Treebank POS tags to Wordnet POS tags. These are the codes which worked fine for me.
import pandas as pd
import string
from nltk import WordPunctTokenizer, pos_tag
from nltk.stem import WordNetLemmatizer
from nltk.corpus import wordnet as wn, stopwords
# Example dataframe
df = pd.DataFrame([[2, "I am new at programming."],
[7, "Leaves are falling from the tree."],
[4, "Sophia has been studying since this morning."]], columns = ['ID', 'Text'])
# Tokenize text
tokenizer = nltk.WordPunctTokenizer()
df["Tokens"] = df["Text"].str.lower().apply(tokenizer.tokenize)
# Remove punctuations
pattern = string.punctuation
print(pattern)
def remove_punctuation(tokens):
filtered = [word for word in tokens if word not in pattern]
return filtered
df["Tokens"] = df["Tokens"].apply(remove_punctuation)
# Remove stopwords
stopwords = stopwords.words('english')
def remove_stopwords(tokens):
filtered_words = [word for word in tokens if word not in stopwords]
return filtered_words
df["Tokens"] = df["Tokens"].apply(remove_stopwords)
The following lines of codes did not work and I got this error:
ValueError: too many values to unpack (expected 2)
def wordnet_pos(pos_tag):
if pos_tag.startswith('J'):
return wn.ADJ
elif pos_tag.startswith('V'):
return wn.VERB
elif pos_tag.startswith('N'):
return wn.NOUN
elif pos_tag.startswith('R'):
return wn.ADV
else:
return None
def wordnet(tokens):
pos_tokens = [nltk.pos_tag(token) for token in tokens]
pos_tokens = [(word, wordnet_pos(pos_tag)) for (word, pos_tag) in pos_tokens]
return pos_tokens
df["Wordnet"] = df["Tokens"].apply(wordnet)
This is what I had hoped to achieve - to create df["Wordnet"] with the Wordnet POS tags.
print(df["Wordnet"])
0 [(new, a), (programming, n)]
1 [(leaves, n), (falling, v), (tree, n)]
2 [(sophia, n), (studying, v), (since, n), (...
Name: Wordnet, dtype: object
Strange error from numpy via matplotlib when trying to get a histogram of a tiny toy dataset. I'm just not sure how to interpret the error, which makes it hard to see what to do next.
Didn't find much related, though this nltk question and this gdsCAD question are superficially similar.
I intend the debugging info at bottom to be more helpful than the driver code, but if I've missed something, please ask. This is reproducible as part of an existing test suite.
if n > 1:
return diff(a[slice1]-a[slice2], n-1, axis=axis)
else:
> return a[slice1]-a[slice2]
E TypeError: ufunc 'subtract' did not contain a loop with signature matching types dtype('<U1') dtype('<U1') dtype('<U1')
../py2.7.11-venv/lib/python2.7/site-packages/numpy/lib/function_base.py:1567: TypeError
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> entering PDB >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
> py2.7.11-venv/lib/python2.7/site-packages/numpy/lib/function_base.py(1567)diff()
-> return a[slice1]-a[slice2]
(Pdb) bt
[...]
py2.7.11-venv/lib/python2.7/site-packages/matplotlib/axes/_axes.py(5678)hist()
-> m, bins = np.histogram(x[i], bins, weights=w[i], **hist_kwargs)
py2.7.11-venv/lib/python2.7/site-packages/numpy/lib/function_base.py(606)histogram()
-> if (np.diff(bins) < 0).any():
> py2.7.11-venv/lib/python2.7/site-packages/numpy/lib/function_base.py(1567)diff()
-> return a[slice1]-a[slice2]
(Pdb) p numpy.__version__
'1.11.0'
(Pdb) p matplotlib.__version__
'1.4.3'
(Pdb) a
a = [u'A' u'B' u'C' u'D' u'E']
n = 1
axis = -1
(Pdb) p slice1
(slice(1, None, None),)
(Pdb) p slice2
(slice(None, -1, None),)
(Pdb)
I got the same error, but in my case I am subtracting dict.key from dict.value. I have fixed this by subtracting dict.value for corresponding key from other dict.value.
cosine_sim = cosine_similarity(e_b-e_a, w-e_c)
here I got error because e_b, e_a and e_c are embedding vector for word a,b,c respectively. I didn't know that 'w' is string, when I sought out w is string then I fix this by following line:
cosine_sim = cosine_similarity(e_b-e_a, word_to_vec_map[w]-e_c)
Instead of subtracting dict.key, now I have subtracted corresponding value for key
I had a similar issue where an integer in a row of a DataFrame I was iterating over was of type numpy.int64. I got the
TypeError: ufunc 'subtract' did not contain a loop with signature matching types dtype('<U1') dtype('<U1') dtype('<U1')
error when trying to subtract a float from it.
The easiest fix for me was to convert the row using pd.to_numeric(row).
Why is it applying diff to an array of strings.
I get an error at the same point, though with a different message
In [23]: a=np.array([u'A' u'B' u'C' u'D' u'E'])
In [24]: np.diff(a)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-24-9d5a62fc3ff0> in <module>()
----> 1 np.diff(a)
C:\Users\paul\AppData\Local\Enthought\Canopy\User\lib\site-packages\numpy\lib\function_base.pyc in diff(a, n, axis)
1112 return diff(a[slice1]-a[slice2], n-1, axis=axis)
1113 else:
-> 1114 return a[slice1]-a[slice2]
1115
1116
TypeError: unsupported operand type(s) for -: 'numpy.ndarray' and 'numpy.ndarray'
Is this a array the bins parameter? What does the docs say bins should be?
I am fairly new to this myself, but I had a similar error and found that it is due to a type casting issue. I was trying to concatenate rather than take the difference but I think the principle is the same here. I provided a similar answer on another question so I hope that is OK.
In essence you need to use a different data type cast, in my case I needed str not float, I suspect yours is the same so my suggested solution is. I am sorry I cannot test it before suggesting but I am unclear from your example what you were doing.
return diff(str(a[slice1])-str(a[slice2]), n-1, axis=axis)
Please see my example code below for the fix to my code, the change occurs on the third to last line. The code is to produce a basic random forest model.
import scipy
import math
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn import preprocessing, metrics, cross_validation
Data = pd.read_csv("Free_Energy_exp.csv", sep=",")
Data = Data.fillna(Data.mean()) # replace the NA values with the mean of the descriptor
header = Data.columns.values # Ues the column headers as the descriptor labels
Data.head()
test_name = "Test.csv"
npArray = np.array(Data)
print header.shape
npheader = np.array(header[1:-1])
print("Array shape X = %d, Y = %d " % (npArray.shape))
datax, datay = npArray.shape
names = npArray[:,0]
X = npArray[:,1:-1].astype(float)
y = npArray[:,-1] .astype(float)
X = preprocessing.scale(X)
XTrain, XTest, yTrain, yTest = cross_validation.train_test_split(X,y, random_state=0)
# Predictions results initialised
RFpredictions = []
RF = RandomForestRegressor(n_estimators = 10, max_features = 5, max_depth = 5, random_state=0)
RF.fit(XTrain, yTrain) # Train the model
print("Training R2 = %5.2f" % RF.score(XTrain,yTrain))
RFpreds = RF.predict(XTest)
with open(test_name,'a') as fpred :
lenpredictions = len(RFpreds)
lentrue = yTest.shape[0]
if lenpredictions == lentrue :
fpred.write("Names/Label,, Prediction Random Forest,, True Value,\n")
for i in range(0,lenpredictions) :
fpred.write(RFpreds[i]+",,"+yTest[i]+",\n")
else :
print "ERROR - names, prediction and true value array size mismatch."
This leads to an error of;
Traceback (most recent call last):
File "min_example.py", line 40, in <module>
fpred.write(RFpreds[i]+",,"+yTest[i]+",\n")
TypeError: ufunc 'add' did not contain a loop with signature matching types dtype('S32') dtype('S32') dtype('S32')
The solution is to make each variable a str() type on the third to last line then write to file. No other changes to then code have been made from the above.
import scipy
import math
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn import preprocessing, metrics, cross_validation
Data = pd.read_csv("Free_Energy_exp.csv", sep=",")
Data = Data.fillna(Data.mean()) # replace the NA values with the mean of the descriptor
header = Data.columns.values # Ues the column headers as the descriptor labels
Data.head()
test_name = "Test.csv"
npArray = np.array(Data)
print header.shape
npheader = np.array(header[1:-1])
print("Array shape X = %d, Y = %d " % (npArray.shape))
datax, datay = npArray.shape
names = npArray[:,0]
X = npArray[:,1:-1].astype(float)
y = npArray[:,-1] .astype(float)
X = preprocessing.scale(X)
XTrain, XTest, yTrain, yTest = cross_validation.train_test_split(X,y, random_state=0)
# Predictions results initialised
RFpredictions = []
RF = RandomForestRegressor(n_estimators = 10, max_features = 5, max_depth = 5, random_state=0)
RF.fit(XTrain, yTrain) # Train the model
print("Training R2 = %5.2f" % RF.score(XTrain,yTrain))
RFpreds = RF.predict(XTest)
with open(test_name,'a') as fpred :
lenpredictions = len(RFpreds)
lentrue = yTest.shape[0]
if lenpredictions == lentrue :
fpred.write("Names/Label,, Prediction Random Forest,, True Value,\n")
for i in range(0,lenpredictions) :
fpred.write(str(RFpreds[i])+",,"+str(yTest[i])+",\n")
else :
print "ERROR - names, prediction and true value array size mismatch."
These examples are from a larger code so I hope the examples are clear enough.
I think #James is right. I got stuck by same error while working on Polyval(). And yeah solution is to use the same type of variabes. You can use typecast to cast all variables in the same type.
BELOW IS A EXAMPLE CODE
import numpy
P = numpy.array(input().split(), float)
x = float(input())
print(numpy.polyval(P,x))
here I used float as an output type. so even the user inputs the INT value (whole number). the final answer will be typecasted to float.
I ran into the same issue, but in my case it was just a Python list instead of a Numpy array used. Using two Numpy arrays solved the issue for me.