01_Aspect_Based_Sentiment_analysis.ipynb on colab

# the above did not work, so use the below for colab
# code is adopted from this site: https://colab.research.google.com/github/stanfordnlp/stanza/blob/master/demo/Stanza_CoreNLP_Interface.ipynb#scrollTo=LS4OKnqJ8wui
"""
# Install stanza
!pip install stanza

# Import stanza
import stanza

# Download the Stanford CoreNLP package with Stanza's installation command
# This'll take several minutes, depending on the network speed
corenlp_dir = './corenlp'
stanza.install_corenlp(dir=corenlp_dir)

# Set the CORENLP_HOME environment variable to point to the installation location
import os
os.environ["CORENLP_HOME"] = corenlp_dir

# Examine the CoreNLP installation folder to make sure the installation is successful
!ls $CORENLP_HOME

# Import client module
from stanza.server import CoreNLPClient

# Construct a CoreNLPClient with some basic annotators, a memory allocation of 4GB, and port number 9001
client = CoreNLPClient(
    annotators=['tokenize','ssplit', 'pos', 'parse', 'lemma', 'ner', 'sentiment'], 
    memory='4G', 
    endpoint='http://localhost:9001',
    be_quiet=True)
print(client)

# Start the background server and wait for some time
# Note that in practice this is totally optional, as by default the server will be started when the first annotation is performed
client.start()
import time; time.sleep(10)

# Print background processes and look for java
# You should be able to see a StanfordCoreNLPServer java process running in the background
!ps -o pid,cmd | grep java

document2 = client.annotate(positive)
# Iterate over all tokens in all sentences, and print out the word, lemma, pos and ner tags
print("{:12s}\t{:12s}\t{:6s}\t{}\t\t{}".format("Word", "Lemma", "POS", "NER", "Sentiment"))

for i, sent in enumerate(document2.sentence):
    print("[Sentence {}]".format(i+1))
    for t in sent.token:
        print("{:12s}\t{:12s}\t{:6s}\t{}\t\t{}".format(t.word, t.lemma, t.pos, t.ner, t.sentiment))
    print("")

document3 = client.annotate(negative)
# Iterate over all tokens in all sentences, and print out the word, lemma, pos and ner tags
print("{:12s}\t{:12s}\t{:6s}\t{}\t\t{}".format("Word", "Lemma", "POS", "NER", "Sentiment"))

for i, sent in enumerate(document3.sentence):
    print("[Sentence {}]".format(i+1))
    for t in sent.token:
        print("{:12s}\t{:12s}\t{:6s}\t{}\t\t{}".format(t.word, t.lemma, t.pos, t.ner, t.sentiment))
    print("")

document4 = client.annotate(ambiguous)
# Iterate over all tokens in all sentences, and print out the word, lemma, pos and ner tags
print("{:12s}\t{:12s}\t{:6s}\t{}\t\t{}".format("Word", "Lemma", "POS", "NER", "Sentiment"))

for i, sent in enumerate(document4.sentence):
    print("[Sentence {}]".format(i+1))
    for t in sent.token:
        print("{:12s}\t{:12s}\t{:6s}\t{}\t\t{}".format(t.word, t.lemma, t.pos, t.ner, t.sentiment))
    print("")

# Shut down the background CoreNLP server
client.stop()

time.sleep(10)
!ps -o pid,cmd | grep java
"""

Author: sony-au

Ch9/01_Aspect_Based_Sentiment_analysis.ipynb

@@ -281,7 +281,8 @@
    "metadata": {},
    "source": [
     "Here you see the model successfully predicts the ambigous sentence which the Varder failed to predict correctly.<br>\n",
-    "The code in this notebook has been adapted from this [article](https://towardsdatascience.com/sentiment-analysis-beyond-words-6ca17a6c1b54)."
+    "The code in this notebook has been adapted from this [article](https://towardsdatascience.com/sentiment-analysis-beyond-words-6ca17a6c1b54).",
+    "See below code for colab."
    ]
   }
  ],