.

Procfile

@@ -0,0 +1 @@
+web: sh setup.sh && streamlit run app.py

README.md

@@ -0,0 +1,7 @@
+To OPEN **NLP News Classifier** click here: 
+
+[![Streamlit APP](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://newsclassifiernlp.herokuapp.com/)
+
+The six categories we want to identify are Sports, Business, Politics, Tech, Entertainment and Health.
+
+

app - Copy.py

@@ -0,0 +1,149 @@
+
+import streamlit as st 
+import joblib,os
+import spacy
+import pandas as pd
+nlp = spacy.load("en_core_web_sm")
+import matplotlib.pyplot as plt 
+import matplotlib
+matplotlib.use("Agg")
+from wordcloud import WordCloud
+
+
+# load Vectorizer 
+complaints_vectorizer = open("models/tfidf_vect.pickle","rb")
+complaints_cv = joblib.load(complaints_vectorizer)
+
+def load_prediction_models(model_file):
+
+	loaded_model = joblib.load(open(os.path.join(model_file),"rb"))
+	return loaded_model
+
+# Get the Keys
+def get_key(val,my_dict):
+	for key,value in my_dict.items():
+		if val == value:
+			return key
+
+
+def main():
+
+	"""Telecom Complaints Classifier"""
+	st.title("Telecom Complaints - Classification App")
+	
+	# Layout Templates
+	html_temp = """
+	<div style="background-color:#464e5f;padding:10px;border-radius:10px;margin:10px;">
+	<h1 style="color:white;text-align:center;"> ML - Telecom Complaints Classifier </h1>
+	<img src="https://www.w3schools.com/howto/img_avatar.png" alt="Avatar" style="vertical-align: middle;width: 50px;height: 50px;border-radius: 50%;" >
+	<p style="text-align:justify">{}</p>
+	</div>
+	"""
+	title_temp ="""
+	<div style="background-color:#464e5f;padding:10px;border-radius:10px;margin:10px;">
+	<h4 style="color:white;text-align:center;">{}</h1>
+	<img src="https://www.w3schools.com/howto/img_avatar.png" alt="Avatar" style="vertical-align: middle;float:left;width: 50px;height: 50px;border-radius: 50%;" >
+	<h6>Author:{}</h6>
+	<br/>
+	<br/> 
+	<p style="text-align:justify">{}</p>
+	</div>
+	"""
+	article_temp ="""
+	<div style="background-color:#464e5f;padding:10px;border-radius:5px;margin:10px;">
+	<h4 style="color:white;text-align:center;">{}</h1>
+	<h6>Author:{}</h6> 
+	<h6>Post Date: {}</h6>
+	<img src="https://www.w3schools.com/howto/img_avatar.png" alt="Avatar" style="vertical-align: middle;width: 50px;height: 50px;border-radius: 50%;" >
+	<br/>
+	<br/>
+	<p style="text-align:justify">{}</p>
+	</div>
+	"""
+
+	
+	st.markdown(html_temp,unsafe_allow_html=True)
+
+	activity = ['Prediction','NLP','About']
+	choice = st.sidebar.selectbox("Select Activity",activity)
+
+
+	if choice == 'Prediction':
+		st.info("Prediction with ML")
+		complaints_text = st.text_area("Enter Complaints Here","Type Here")
+		all_ml_models = ["Decision Tree", "GradientBoost"]
+		model_choice = st.selectbox("Select Model",all_ml_models)
+
+		prediction_labels = {'Closed': 0, 'Open': 1, 'Pending': 2, 'Solved': 3}
+		if st.button("Classify"):
+			st.text("Original Text:\n{}".format(complaints_text))
+			vect_text = complaints_cv.transform([complaints_text]).toarray()
+			if model_choice == 'Decision Tree':
+				predictor = load_prediction_models("models/dtcpred.pickle")
+				prediction = predictor.predict(vect_text)
+				# st.write(prediction)
+			elif model_choice == 'GradientBoost':
+				predictor = load_prediction_models("models/gbcpred.pickle")
+				prediction = predictor.predict(vect_text)
+				# st.write(prediction)
+                
+                
+			final_result = get_key(prediction,prediction_labels)
+			st.success("Complaints Categorized as: {}".format(final_result))
+
+	elif choice == 'NLP':
+		st.info("Natural Language Processing of Text")
+		raw_text = st.text_area("Enter Customer Complaints Here","Type Here")
+		nlp_task = ["Tokenization","Lemmatization","Named Entity Recognition(NER)","Parts-of-Speech(POS) Tags"]
+		task_choice = st.selectbox("Choose NLP Task",nlp_task)
+		if st.button("Analyze"):
+			st.info("Original Text:\n{}".format(raw_text))
+
+			docx = nlp(raw_text)
+			if task_choice == 'Tokenization':
+				result = [token.text for token in docx ]
+			elif task_choice == 'Lemmatization':
+				result = ["'Token':{},'Lemma':{}".format(token.text,token.lemma_) for token in docx]
+			elif task_choice == 'Named Entity Recognition(NER)':
+				result = [(entity.text,entity.label_)for entity in docx.ents]
+			elif task_choice == 'Parts-of-Speech(POS) Tags':
+				result = ["'Token':{},'POS':{},'Dependency':{}".format(word.text,word.tag_,word.dep_) for word in docx]
+
+			st.json(result)
+
+		if st.button("Tabulize"):
+			docx = nlp(raw_text)
+			c_tokens = [token.text for token in docx ]
+			c_lemma = [token.lemma_ for token in docx ]
+			c_pos = [token.pos_ for token in docx ]
+
+			new_df = pd.DataFrame(zip(c_tokens,c_lemma,c_pos),columns=['Tokens','Lemma','POS'])
+			st.dataframe(new_df)
+
+
+		if st.checkbox("WordCloud"):
+			c_text = raw_text
+			wordcloud = WordCloud().generate(c_text)
+			plt.imshow(wordcloud,interpolation='bilinear')
+			plt.axis("off")
+			st.set_option('deprecation.showPyplotGlobalUse', False)
+			st.pyplot()
+
+	else:
+		st.write("")
+		st.subheader("About")
+		st.write("")
+	
+		st.markdown("""
+        ### NLP Complaints Classifier With Different Models (With Streamlit)
+        Python Tools Used: spacy, pandas, matplotlib, wordcloud, Pillow(PIL), Joblib
+        """)
+
+
+if __name__ == '__main__':
+	main()
+	
+	
+	
+    
+    

app.py

@@ -0,0 +1,159 @@
+import streamlit as st
+import joblib,os
+import scipy
+import spacy
+import pandas as pd
+nlp = spacy.load("en_core_web_sm")
+import matplotlib.pyplot as plt
+import matplotlib
+matplotlib.use("Agg")
+from wordcloud import WordCloud
+
+
+# load Vectorizer
+complaints_vectorizer = open("models/tfidf_vect.joblib","rb")
+complaints_cv = joblib.load(complaints_vectorizer)
+
+def load_prediction_models(model_file):
+
+	loaded_model = joblib.load(open(os.path.join(model_file),"rb"))
+	return loaded_model
+
+# Get the Keys
+def get_key(val,my_dict):
+	for key,value in my_dict.items():
+		if val == value:
+			return key
+
+
+
+
+def main():
+
+	"""Telecom Complaints Classifier"""
+	st.title("Comcast Telecom Complaints App")
+	
+	# Layout Templates
+	html_temp = """
+	<div style="background-color:#D5CC8F;padding:10px;border-radius:10px;margin:10px;">
+	<h1 style="color:white;text-align:center;"> ML - Telecom Complaints Classifier </h1>
+	<img src="https://www.w3schools.com/howto/img_avatar.png" alt="Avatar" style="vertical-align: middle;width: 50px;height: 50px;border-radius: 50%;" >
+	<p style="text-align:justify">{}</p>
+	</div>
+	"""
+	title_temp ="""
+	<div style="background-color:#D5CC8F;padding:10px;border-radius:10px;margin:10px;">
+	<h4 style="color:white;text-align:center;">{Debmalya Ray}</h1>
+	<img src="https://www.w3schools.com/howto/img_avatar.png" alt="Avatar" style="vertical-align: middle;float:left;width: 50px;height: 50px;border-radius: 50%;" >
+	<h6>Author:{Debmalya Ray}</h6>
+	<br/>
+	<br/>
+	<p style="text-align:justify">{}</p>
+	</div>
+	"""
+	article_temp ="""
+	<div style="background-color:#D5CC8F;padding:10px;border-radius:5px;margin:10px;">
+	<h4 style="color:white;text-align:center;">{Debmalya Ray}</h1>
+	<h6>Author:{Debmalya Ray}</h6>
+	<h6>Post Date: {}</h6>
+	<img src="https://www.w3schools.com/howto/img_avatar.png" alt="Avatar" style="vertical-align: middle;width: 50px;height: 50px;border-radius: 50%;" >
+	<br/>
+	<br/>
+	<p style="text-align:justify">{}</p>
+	</div>
+	"""
+
+
+	st.markdown(html_temp,unsafe_allow_html=True)
+
+	activity = ['Prediction','NLP','About']
+	choice = st.sidebar.selectbox("Select Activity",activity)
+
+
+	if choice == 'Prediction':
+		st.info("Prediction with ML")
+		complaints_text = st.text_area("Enter Complaints Here","Type Here")
+		all_ml_models = ["Decision Tree", "GradientBoost"]
+		model_choice = st.selectbox("Select Model",all_ml_models)
+
+		prediction_labels = {'Closed': 0, 'Open': 1, 'Pending': 2, 'Solved': 3}
+		if st.button("Classify"):
+			st.text("Original Text:\n{}".format(complaints_text))
+			vect_text = complaints_cv.transform([complaints_text]).toarray()
+			if model_choice == 'Decision Tree':
+				predictor = load_prediction_models("models/dtcpred.joblib")
+				prediction = predictor.predict(vect_text)
+				st.write(prediction)
+			elif model_choice == 'GradientBoost':
+				predictor = load_prediction_models("models/gbcpred.joblib")
+				prediction = predictor.predict(vect_text)
+				st.write(prediction)
+
+			final_result = get_key(prediction,prediction_labels)
+			st.success("Complaints Categorized as: {}".format(final_result))
+
+	elif choice == 'NLP':
+		st.info("Natural Language Processing of Text")
+		raw_text = st.text_area("Enter Customer Complaints Here","Type Here")
+		nlp_task = ["Tokenization","Lemmatization","Named Entity Recognition(NER)","Parts-of-Speech(POS) Tags"]
+		task_choice = st.selectbox("Choose NLP Task",nlp_task)
+		if st.button("Analyze"):
+			st.info("Original Text:\n{}".format(raw_text))
+
+			docx = nlp(raw_text)
+			if task_choice == 'Tokenization':
+				result = [token.text for token in docx ]
+			elif task_choice == 'Lemmatization':
+				result = ["'Token':{},'Lemma':{}".format(token.text,token.lemma_) for token in docx]
+			elif task_choice == 'Named Entity Recognition(NER)':
+				result = [(entity.text,entity.label_)for entity in docx.ents]
+			elif task_choice == 'Parts-of-Speech(POS) Tags':
+				result = ["'Token':{},'POS':{},'Dependency':{}".format(word.text,word.tag_,word.dep_) for word in docx]
+
+			st.json(result)
+
+		if st.button("Tabulize"):
+			docx = nlp(raw_text)
+			c_tokens = [token.text for token in docx ]
+			c_lemma = [token.lemma_ for token in docx ]
+			c_pos = [token.pos_ for token in docx ]
+
+			new_df = pd.DataFrame(zip(c_tokens,c_lemma,c_pos),columns=['Tokens','Lemma','POS'])
+			st.dataframe(new_df)
+
+
+		if st.checkbox("WordCloud"):
+			c_text = raw_text
+			wordcloud = WordCloud().generate(c_text)
+			plt.imshow(wordcloud,interpolation='bilinear')
+			plt.axis("off")
+			st.set_option('deprecation.showPyplotGlobalUse', False)
+			st.pyplot()
+
+	else:
+		st.write("")
+		st.subheader("About")
+		st.write("""**************************************************************************""")
+		st.markdown("""
+        ### NLP Complaints Classifier With Different Models (With Streamlit)
+        ###### Python Tools Used: spacy, pandas, matplotlib, wordcloud, Pillow(PIL), Joblib
+        """)
+		st.write("""**************************************************************************""")
+		st.write("""
+        361148 || Throttling service and unreasonable data caps	 || 24-06-2015 || Acworth || Georgia || 30101 || Pending  
+        """)
+		st.write("""
+        359792 || Comcast refuses to help troubleshoot and correct my service. || 23-06-2015 || Adrian || Michigan || 49221 || Solved 
+        """)
+		st.write("""
+        371214 || Comcast Raising Prices and Not Being Available To Ask Why || 28-06-2015 || Alameda || California || 94501 || Open  
+        """)
+		st.write("""
+        242732 || Speed and Service || 18-04-2015 || Acworth || Georgia || 30101 || Closed
+        """)
+		st.write("""**************************************************************************""")
+
+
+if __name__ == '__main__':
+	main()
+ 

req.txt

@@ -0,0 +1,558 @@
+absl-py==1.3.0
+accelerate==0.19.0
+aiofiles==22.1.0
+aiohttp @ file:///C:/ci/aiohttp_1646806572557/work
+aiosignal @ file:///tmp/build/80754af9/aiosignal_1637843061372/work
+aiosqlite==0.17.0
+alabaster @ file:///home/ktietz/src/ci/alabaster_1611921544520/work
+alembic==1.8.1
+alpha-vantage==2.3.1
+altair==4.2.0
+anaconda-client @ file:///C:/ci/anaconda-client_1635342725944/work
+anaconda-navigator==2.3.2
+anaconda-project @ file:///tmp/build/80754af9/anaconda-project_1637161053845/work
+anyio @ file:///C:/ci/anyio_1644481921011/work/dist
+appdirs==1.4.4
+argon2-cffi @ file:///opt/conda/conda-bld/argon2-cffi_1645000214183/work
+argon2-cffi-bindings @ file:///C:/ci/argon2-cffi-bindings_1644551690056/work
+arrow @ file:///opt/conda/conda-bld/arrow_1649166651673/work
+asgiref==3.5.2
+astor==0.8.1
+astroid @ file:///C:/ci/astroid_1628063282661/work
+astropy @ file:///C:/ci/astropy_1650634291321/work
+asttokens @ file:///opt/conda/conda-bld/asttokens_1646925590279/work
+astunparse==1.6.3
+async-timeout @ file:///tmp/build/80754af9/async-timeout_1637851218186/work
+atomicwrites==1.4.0
+attrs @ file:///opt/conda/conda-bld/attrs_1642510447205/work
+audioread==3.0.0
+Automat @ file:///tmp/build/80754af9/automat_1600298431173/work
+autopage==0.5.1
+autopep8 @ file:///opt/conda/conda-bld/autopep8_1639166893812/work
+Babel @ file:///tmp/build/80754af9/babel_1620871417480/work
+backcall @ file:///home/ktietz/src/ci/backcall_1611930011877/work
+backports.functools-lru-cache @ file:///tmp/build/80754af9/backports.functools_lru_cache_1618170165463/work
+backports.tempfile @ file:///home/linux1/recipes/ci/backports.tempfile_1610991236607/work
+backports.weakref==1.0.post1
+base58==2.1.1
+bcrypt @ file:///C:/ci/bcrypt_1607022693089/work
+beautifulsoup4 @ file:///C:/ci/beautifulsoup4_1650293025093/work
+binaryornot @ file:///tmp/build/80754af9/binaryornot_1617751525010/work
+bitarray @ file:///C:/ci/bitarray_1648739663053/work
+bkcharts==0.2
+black==19.10b0
+bleach @ file:///opt/conda/conda-bld/bleach_1641577558959/work
+blinker==1.5
+blis==0.7.9
+bokeh @ file:///C:/ci/bokeh_1638362966927/work
+boto3 @ file:///opt/conda/conda-bld/boto3_1649078879353/work
+botocore @ file:///opt/conda/conda-bld/botocore_1649076662316/work
+Bottleneck @ file:///C:/ci/bottleneck_1648010904582/work
+Brotli==1.0.9
+brotlipy==0.7.0
+cachetools @ file:///tmp/build/80754af9/cachetools_1619597386817/work
+catalogue==1.0.2
+catboost==1.2
+category-encoders==2.5.1.post0
+certifi==2022.12.7
+cffi @ file:///C:/ci_310/cffi_1642682485096/work
+chardet==3.0.4
+charset-normalizer @ file:///tmp/build/80754af9/charset-normalizer_1630003229654/work
+click==8.1.3
+cliff==4.1.0
+cloudpickle @ file:///tmp/build/80754af9/cloudpickle_1632508026186/work
+clyent==1.2.2
+cmaes==0.9.0
+cmd2==2.4.2
+cmdstanpy==1.0.8
+colabcode==0.3.0
+colorama @ file:///tmp/build/80754af9/colorama_1607707115595/work
+colorcet @ file:///tmp/build/80754af9/colorcet_1611168489822/work
+colorlog==6.7.0
+commonmark==0.9.1
+comtypes==1.1.10
+conda==22.9.0
+conda-build==3.21.8
+conda-content-trust @ file:///tmp/build/80754af9/conda-content-trust_1617045594566/work
+conda-pack @ file:///tmp/build/80754af9/conda-pack_1611163042455/work
+conda-package-handling @ file:///C:/b/abs_81m11h_i4r/croots/recipe/conda-package-handling_1663598470202/work
+conda-repo-cli @ file:///tmp/build/80754af9/conda-repo-cli_1620168426516/work
+conda-token @ file:///tmp/build/80754af9/conda-token_1620076980546/work
+conda-verify==3.4.2
+confection==0.0.3
+constantly==15.1.0
+convertdate==2.4.0
+cookiecutter @ file:///opt/conda/conda-bld/cookiecutter_1649151442564/work
+cryptography @ file:///C:/ci/cryptography_1633520531101/work
+cssselect==1.1.0
+cycler @ file:///tmp/build/80754af9/cycler_1637851556182/work
+cymem==2.0.7
+Cython @ file:///C:/ci/cython_1647850559892/work
+cytoolz==0.11.0
+daal4py==2021.5.0
+dash==2.9.3
+dash-core-components==2.0.0
+dash-html-components==2.0.0
+dash-table==5.0.0
+dashboard==0.0.6
+dask @ file:///opt/conda/conda-bld/dask-core_1647268715755/work
+databases==0.6.1
+datasets==2.12.0
+datashader @ file:///tmp/build/80754af9/datashader_1623782308369/work
+datashape==0.5.4
+deap==1.3.3
+debugpy @ file:///C:/ci/debugpy_1637091961445/work
+decorator @ file:///opt/conda/conda-bld/decorator_1643638310831/work
+defusedxml @ file:///tmp/build/80754af9/defusedxml_1615228127516/work
+Deprecated==1.2.13
+diff-match-patch @ file:///Users/ktietz/demo/mc3/conda-bld/diff-match-patch_1630511840874/work
+dill==0.3.6
+distlib==0.3.6
+distributed @ file:///opt/conda/conda-bld/distributed_1647271944416/work
+Django==4.1.2
+django-admin-rangefilter==0.9.0
+django-allauth==0.51.0
+django-crispy-forms==1.14.0
+django-extensions==3.2.1
+django-filter==22.1
+django-multiselectfield==0.1.12
+django-storages==1.13.1
+docutils @ file:///C:/ci/docutils_1620828264669/work
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.3.1/en_core_web_sm-2.3.1.tar.gz
+ensure==1.0.2
+entrypoints @ file:///C:/ci/entrypoints_1649926621128/work
+ephem==4.1.3
+et-xmlfile==1.1.0
+executing @ file:///opt/conda/conda-bld/executing_1646925071911/work
+fastapi==0.78.0
+fastdist==1.1.5
+fastjsonschema @ file:///tmp/build/80754af9/python-fastjsonschema_1620414857593/work/dist
+filelock @ file:///opt/conda/conda-bld/filelock_1647002191454/work
+flake8 @ file:///tmp/build/80754af9/flake8_1620776156532/work
+Flask==2.2.3
+flatbuffers==22.9.24
+fonttools==4.25.0
+frozenlist @ file:///C:/ci/frozenlist_1637767271796/work
+fsspec @ file:///opt/conda/conda-bld/fsspec_1647268051896/work
+future @ file:///C:/ci/future_1607568713721/work
+gast==0.4.0
+gensim @ file:///C:/ci/gensim_1646825438310/work
+git-lfs==1.6
+gitdb==4.0.10
+GitPython==3.1.29
+glob2 @ file:///home/linux1/recipes/ci/glob2_1610991677669/work
+google==3.0.0
+google-api-core @ file:///C:/ci/google-api-core-split_1613980333946/work
+google-auth==2.19.1
+google-auth-oauthlib==1.0.0
+google-cloud==0.34.0
+google-cloud-core @ file:///tmp/build/80754af9/google-cloud-core_1625077425256/work
+google-cloud-storage @ file:///tmp/build/80754af9/google-cloud-storage_1601307969662/work
+google-crc32c @ file:///C:/ci/google-crc32c_1613234249694/work
+google-pasta==0.2.0
+google-resumable-media @ file:///tmp/build/80754af9/google-resumable-media_1624367812531/work
+googleapis-common-protos @ file:///C:/ci/googleapis-common-protos-feedstock_1617957814607/work
+graphviz==0.20.1
+greenlet @ file:///C:/ci/greenlet_1628888275363/work
+grpcio==1.54.2
+gunicorn==20.1.0
+gym==0.26.2
+gym-notices==0.0.8
+h11==0.14.0
+h5py @ file:///C:/ci/h5py_1637120894255/work
+HeapDict @ file:///Users/ktietz/demo/mc3/conda-bld/heapdict_1630598515714/work
+hijri-converter==2.2.4
+holidays==0.17.2
+holoviews @ file:///opt/conda/conda-bld/holoviews_1645454331194/work
+htmlmin==0.1.12
+httplib2==0.20.4
+huggingface-hub==0.15.1
+hvplot @ file:///tmp/build/80754af9/hvplot_1627305124151/work
+hyperlink @ file:///tmp/build/80754af9/hyperlink_1610130746837/work
+idna==2.10
+imagecodecs @ file:///C:/ci/imagecodecs_1635511087451/work
+ImageHash==4.3.1
+imageio @ file:///tmp/build/80754af9/imageio_1617700267927/work
+imagesize @ file:///tmp/build/80754af9/imagesize_1637939814114/work
+imbalanced-learn==0.9.1
+import-ipynb==0.1.4
+importlib-metadata @ file:///C:/ci/importlib-metadata_1648562621412/work
+importlib-resources==5.10.0
+incremental @ file:///tmp/build/80754af9/incremental_1636629750599/work
+inflate64==0.3.1
+inflection==0.5.1
+iniconfig @ file:///home/linux1/recipes/ci/iniconfig_1610983019677/work
+intake @ file:///opt/conda/conda-bld/intake_1647436631684/work
+intervaltree @ file:///Users/ktietz/demo/mc3/conda-bld/intervaltree_1630511889664/work
+ipykernel @ file:///C:/ci/ipykernel_1646982785443/work/dist/ipykernel-6.9.1-py3-none-any.whl
+ipython @ file:///C:/ci/ipython_1648817223581/work
+ipython-genutils @ file:///tmp/build/80754af9/ipython_genutils_1606773439826/work
+ipywidgets @ file:///tmp/build/80754af9/ipywidgets_1634143127070/work
+isort @ file:///tmp/build/80754af9/isort_1628603791788/work
+itemadapter @ file:///tmp/build/80754af9/itemadapter_1626442940632/work
+itemloaders @ file:///opt/conda/conda-bld/itemloaders_1646805235997/work
+itsdangerous==2.1.2
+jax==0.4.11
+jdcal @ file:///Users/ktietz/demo/mc3/conda-bld/jdcal_1630584345063/work
+jedi @ file:///C:/ci/jedi_1644315428289/work
+Jinja2==3.1.2
+jinja2-time @ file:///opt/conda/conda-bld/jinja2-time_1649251842261/work
+jmespath @ file:///Users/ktietz/demo/mc3/conda-bld/jmespath_1630583964805/work
+joblib==1.2.0
+json5 @ file:///tmp/build/80754af9/json5_1624432770122/work
+jsonify==0.5
+jsonschema @ file:///C:/ci/jsonschema_1650008058050/work
+jupyter @ file:///C:/ci/jupyter_1607685287094/work
+jupyter-client @ file:///tmp/build/80754af9/jupyter_client_1616770841739/work
+jupyter-console @ file:///tmp/build/80754af9/jupyter_console_1616615302928/work
+jupyter-server==1.23.5
+jupyter_core==5.1.3
+jupyterlab==3.0.7
+jupyterlab-pygments @ file:///tmp/build/80754af9/jupyterlab_pygments_1601490720602/work
+jupyterlab-server @ file:///opt/conda/conda-bld/jupyterlab_server_1644500396812/work
+jupyterlab-widgets @ file:///tmp/build/80754af9/jupyterlab_widgets_1609884341231/work
+jws==0.1.3
+kaleido==0.2.1
+keras==2.12.0
+Keras-Preprocessing==1.1.2
+keyring @ file:///C:/ci/keyring_1638531673471/work
+kiwisolver @ file:///C:/ci/kiwisolver_1644962577370/work
+klib==1.0.4
+korean-lunar-calendar==0.3.1
+langcodes==3.3.0
+lazy-object-proxy @ file:///C:/ci/lazy-object-proxy_1616529288960/work
+lazy_loader==0.2
+libarchive-c @ file:///tmp/build/80754af9/python-libarchive-c_1617780486945/work
+libclang==14.0.6
+librosa==0.10.0.post2
+lightgbm==3.3.3
+llvmlite==0.38.0
+locket @ file:///C:/ci/locket_1647006279389/work
+LunarCalendar==0.0.9
+lxml @ file:///C:/ci/lxml_1646642862366/work
+Mako==1.2.4
+Markdown @ file:///C:/ci/markdown_1614364082838/work
+MarkupSafe==2.1.2
+matplotlib @ file:///C:/ci/matplotlib-suite_1647423638658/work
+matplotlib-inline @ file:///tmp/build/80754af9/matplotlib-inline_1628242447089/work
+mccabe==0.6.1
+menuinst @ file:///C:/ci/menuinst_1631733438520/work
+mistune==2.0.4
+mkl-fft==1.3.1
+mkl-random @ file:///C:/ci/mkl_random_1626186184308/work
+mkl-service==2.4.0
+ml-dtypes==0.1.0
+# Editable Git install with no remote (mlproject==0.0.1)
+-e e:\ml_oop\mlproject_airbnb\mlproject_airbnb
+# Editable Git install with no remote (mlproject-telecom==0.0.1)
+-e e:\ml_oop\mlproject_telecom\mlproject_telecom
+mock @ file:///tmp/build/80754af9/mock_1607622725907/work
+mpmath==1.2.1
+msgpack @ file:///C:/ci/msgpack-python_1612287350784/work
+multidict @ file:///C:/ci/multidict_1607349747897/work
+multimethod==1.9
+multipledispatch @ file:///C:/ci/multipledispatch_1607574329826/work
+multiprocess==0.70.14
+multitasking==0.0.11
+multivolumefile==0.2.3
+munkres==1.1.4
+murmurhash==1.0.9
+mypy-boto3-s3==1.26.127
+mypy-extensions==0.4.3
+mysqlclient==2.1.1
+navigator-updater==0.2.1
+nbclassic @ file:///opt/conda/conda-bld/nbclassic_1644943264176/work
+nbclient @ file:///C:/ci/nbclient_1650290387259/work
+nbconvert==7.2.8
+nbformat @ file:///C:/ci/nbformat_1649845125000/work
+neattext==0.1.3
+nest-asyncio==1.4.3
+networkx @ file:///opt/conda/conda-bld/networkx_1647437648384/work
+nltk @ file:///opt/conda/conda-bld/nltk_1645628263994/work
+nose @ file:///opt/conda/conda-bld/nose_1642704612149/work
+notebook==6.4.5
+notebook-as-pdf==0.5.0
+numba @ file:///C:/ci/numba_1650394399948/work
+numexpr @ file:///C:/ci/numexpr_1640704337920/work
+numpy==1.21.0
+numpydoc @ file:///opt/conda/conda-bld/numpydoc_1643788541039/work
+oauth2client==3.0.0
+oauthlib==3.2.2
+olefile @ file:///Users/ktietz/demo/mc3/conda-bld/olefile_1629805411829/work
+openpyxl @ file:///tmp/build/80754af9/openpyxl_1632777717936/work
+opt-einsum==3.3.0
+optuna==3.0.3
+orm==0.2.0.dev1
+packaging @ file:///tmp/build/80754af9/packaging_1637314298585/work
+pandas==1.3.5
+pandas-datareader==0.10.0
+pandas-profiling==3.5.0
+pandas-visual-analysis==0.0.4
+pandocfilters @ file:///opt/conda/conda-bld/pandocfilters_1643405455980/work
+panel @ file:///C:/ci/panel_1650623703033/work
+param @ file:///tmp/build/80754af9/param_1636647414893/work
+paramiko @ file:///opt/conda/conda-bld/paramiko_1640109032755/work
+parsel @ file:///C:/ci/parsel_1646740216444/work
+parso @ file:///opt/conda/conda-bld/parso_1641458642106/work
+partd @ file:///opt/conda/conda-bld/partd_1647245470509/work
+pathspec==0.7.0
+pathy==0.10.0
+patsy==0.5.2
+pbr==5.11.0
+pep8==1.7.1
+pexpect @ file:///tmp/build/80754af9/pexpect_1605563209008/work
+phik==0.12.2
+pickleshare @ file:///tmp/build/80754af9/pickleshare_1606932040724/work
+Pillow==9.0.1
+pkginfo @ file:///tmp/build/80754af9/pkginfo_1643162084911/work
+plac==1.1.3
+platformdirs==2.5.2
+plotly @ file:///opt/conda/conda-bld/plotly_1646671701182/work
+pluggy @ file:///C:/ci/pluggy_1648024580010/work
+pmdarima==2.0.1
+pooch==1.6.0
+portalocker==2.7.0
+poyo @ file:///tmp/build/80754af9/poyo_1617751526755/work
+preshed==3.0.8
+prettytable==3.5.0
+prometheus-client @ file:///opt/conda/conda-bld/prometheus_client_1643788673601/work
+prompt-toolkit @ file:///tmp/build/80754af9/prompt-toolkit_1633440160888/work
+prophet==1.1.1
+Protego @ file:///tmp/build/80754af9/protego_1598657180827/work
+protobuf==3.20.3
+psutil @ file:///C:/ci/psutil_1612298199233/work
+ptyprocess @ file:///tmp/build/80754af9/ptyprocess_1609355006118/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
+pure-eval @ file:///opt/conda/conda-bld/pure_eval_1646925070566/work
+py @ file:///opt/conda/conda-bld/py_1644396412707/work
+py7zr==0.20.5
+pyarrow==10.0.1
+pyasn1 @ file:///Users/ktietz/demo/mc3/conda-bld/pyasn1_1629708007385/work
+pyasn1-modules==0.2.8
+pybcj==1.0.1
+pycaret-ts-alpha==3.0.0.dev1649017462
+pycodestyle==2.10.0
+pycosat==0.6.3
+pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
+pycryptodome==3.15.0
+pycryptodomex==3.18.0
+pyct @ file:///C:/ci/pyct_1613411728548/work
+pycurl==7.44.1
+pydantic==1.10.2
+pydeck==0.8.0
+PyDispatcher==2.0.5
+pydocstyle @ file:///tmp/build/80754af9/pydocstyle_1621600989141/work
+pyee==8.2.2
+pyerfa @ file:///C:/ci/pyerfa_1621560974055/work
+pyflakes @ file:///tmp/build/80754af9/pyflakes_1617200973297/work
+Pygments @ file:///opt/conda/conda-bld/pygments_1644249106324/work
+PyHamcrest @ file:///tmp/build/80754af9/pyhamcrest_1615748656804/work
+PyJWT @ file:///C:/ci/pyjwt_1657511236979/work
+pylint @ file:///C:/ci/pylint_1627536884966/work
+pyls-spyder==0.4.0
+PyMeeus==0.5.11
+Pympler==1.0.1
+PyMySQL==1.0.2
+PyNaCl @ file:///C:/ci/pynacl_1607612759007/work
+pyngrok==5.1.0
+pyod==1.0.6
+pyodbc @ file:///C:/ci/pyodbc_1647426110990/work
+pyOpenSSL @ file:///tmp/build/80754af9/pyopenssl_1635333100036/work
+pyparsing @ file:///tmp/build/80754af9/pyparsing_1635766073266/work
+PyPDF2==3.0.1
+pyperclip==1.8.2
+pyppeteer==1.0.2
+pyppmd==1.0.0
+PyQt5==5.15.9
+PyQt5-Qt5==5.15.2
+PyQt5-sip==12.12.1
+PyQtWebEngine==5.15.6
+PyQtWebEngine-Qt5==5.15.2
+pyreadline==2.1
+pyreadline3==3.4.1
+pyrsistent @ file:///C:/ci/pyrsistent_1636093225342/work
+PySocks @ file:///C:/ci/pysocks_1605307512533/work
+pytest==7.1.1
+python-box==6.0.2
+python-dateutil @ file:///tmp/build/80754af9/python-dateutil_1626374649649/work
+python-jwt==2.0.1
+python-lsp-black @ file:///tmp/build/80754af9/python-lsp-black_1634232156041/work
+python-lsp-jsonrpc==1.0.0
+python-lsp-server==1.2.4
+python-multipart==0.0.5
+python-slugify @ file:///tmp/build/80754af9/python-slugify_1620405669636/work
+python-snappy @ file:///C:/ci/python-snappy_1610133405910/work
+python3-openid==3.2.0
+pytz==2021.3
+pytz-deprecation-shim==0.1.0.post0
+pyviz-comms @ file:///tmp/build/80754af9/pyviz_comms_1623747165329/work
+PyWavelets @ file:///C:/ci/pywavelets_1648728084106/work
+pywin32==302
+pywin32-ctypes @ file:///C:/ci/pywin32-ctypes_1607553594546/work
+pywinpty==1.1.6
+PyYAML==6.0
+pyzmq @ file:///C:/ci/pyzmq_1638435148211/work
+pyzstd==0.15.7
+QDarkStyle @ file:///tmp/build/80754af9/qdarkstyle_1617386714626/work
+qstylizer @ file:///tmp/build/80754af9/qstylizer_1617713584600/work/dist/qstylizer-0.1.10-py2.py3-none-any.whl
+QtAwesome @ file:///tmp/build/80754af9/qtawesome_1637160816833/work
+qtconsole @ file:///opt/conda/conda-bld/qtconsole_1649078897110/work
+QtPy @ file:///opt/conda/conda-bld/qtpy_1649073884068/work
+queuelib==1.5.0
+rake-nltk==1.0.6
+regex @ file:///C:/ci/regex_1648447888413/work
+requests==2.28.1
+requests-file @ file:///Users/ktietz/demo/mc3/conda-bld/requests-file_1629455781986/work
+requests-oauthlib==1.3.1
+requests-toolbelt==0.7.0
+responses==0.18.0
+rich==12.6.0
+river==0.14.0
+rope @ file:///opt/conda/conda-bld/rope_1643788605236/work
+rouge-score==0.1.2
+rsa @ file:///tmp/build/80754af9/rsa_1614366226499/work
+Rtree @ file:///C:/ci/rtree_1618421015405/work
+ruamel-yaml-conda @ file:///C:/ci/ruamel_yaml_1616016898638/work
+s3transfer @ file:///tmp/build/80754af9/s3transfer_1626435152308/work
+sacrebleu==2.3.1
+scikit-image @ file:///C:/ci/scikit-image_1648214340990/work
+scikit-learn==1.2.2
+scikit-learn-intelex==2021.20220215.102710
+scikit-plot==0.3.7
+scipy==1.9.3
+Scrapy @ file:///C:/ci/scrapy_1646837986255/work
+seaborn==0.11.1
+semver==2.13.0
+Send2Trash @ file:///tmp/build/80754af9/send2trash_1632406701022/work
+sentencepiece==0.1.99
+service-identity @ file:///Users/ktietz/demo/mc3/conda-bld/service_identity_1629460757137/work
+setuptools-git==1.2
+sip==4.19.13
+six @ file:///tmp/build/80754af9/six_1644875935023/work
+sklearn==0.0.post1
+sktime==0.10.1
+smart-open==5.2.1
+smmap==5.0.0
+sniffio @ file:///C:/ci/sniffio_1614030527509/work
+snowballstemmer @ file:///tmp/build/80754af9/snowballstemmer_1637937080595/work
+sortedcollections @ file:///tmp/build/80754af9/sortedcollections_1611172717284/work
+sortedcontainers @ file:///tmp/build/80754af9/sortedcontainers_1623949099177/work
+soundfile==0.12.1
+soupsieve @ file:///tmp/build/80754af9/soupsieve_1636706018808/work
+soxr==0.3.5
+spacy==2.3.9
+spacy-legacy==3.0.10
+spacy-loggers==1.0.3
+Sphinx @ file:///opt/conda/conda-bld/sphinx_1643644169832/work
+sphinxcontrib-applehelp @ file:///home/ktietz/src/ci/sphinxcontrib-applehelp_1611920841464/work
+sphinxcontrib-devhelp @ file:///home/ktietz/src/ci/sphinxcontrib-devhelp_1611920923094/work
+sphinxcontrib-htmlhelp @ file:///tmp/build/80754af9/sphinxcontrib-htmlhelp_1623945626792/work
+sphinxcontrib-jsmath @ file:///home/ktietz/src/ci/sphinxcontrib-jsmath_1611920942228/work
+sphinxcontrib-qthelp @ file:///home/ktietz/src/ci/sphinxcontrib-qthelp_1611921055322/work
+sphinxcontrib-serializinghtml @ file:///tmp/build/80754af9/sphinxcontrib-serializinghtml_1624451540180/work
+spyder @ file:///C:/ci/spyder_1636480369575/work
+spyder-kernels @ file:///C:/ci/spyder-kernels_1634237096710/work
+SQLAlchemy @ file:///C:/ci/sqlalchemy_1647600017103/work
+sqlparse==0.4.3
+srsly==1.0.6
+stack-data @ file:///opt/conda/conda-bld/stack_data_1646927590127/work
+starlette==0.19.1
+statsmodels==0.13.2
+stevedore==4.1.1
+stochastic==0.7.0
+stopit==1.1.2
+streamlit==1.25.0
+streamlit-theme==0.58.0
+sweetviz==2.1.4
+sympy @ file:///C:/ci/sympy_1647853873858/work
+tables==3.6.1
+tabulate==0.8.9
+tangled-up-in-unicode==0.2.0
+tbats==1.1.1
+TBB==0.2
+tblib @ file:///Users/ktietz/demo/mc3/conda-bld/tblib_1629402031467/work
+tenacity==8.2.3
+tensorboard==2.12.3
+tensorboard-data-server==0.7.0
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.12.0
+tensorflow-estimator==2.12.0
+tensorflow-intel==2.12.0
+tensorflow-io==0.31.0
+tensorflow-io-gcs-filesystem==0.31.0
+tensortrade==1.0.3
+termcolor==2.0.1
+terminado @ file:///C:/ci/terminado_1644322780199/work
+testpath @ file:///tmp/build/80754af9/testpath_1624638946665/work
+text-summarizer==0.0.6
+text-unidecode @ file:///Users/ktietz/demo/mc3/conda-bld/text-unidecode_1629401354553/work
+textblob==0.17.1
+textdistance @ file:///tmp/build/80754af9/textdistance_1612461398012/work
+# Editable install with no version control (textSummarizer==0.0.0)
+-e e:\ml_oop\text-summarization-nlp-project-main\src
+texttable==1.6.7
+thinc==7.4.6
+threadpoolctl==2.1.0
+three-merge @ file:///tmp/build/80754af9/three-merge_1607553261110/work
+tifffile @ file:///tmp/build/80754af9/tifffile_1627275862826/work
+tinycss @ file:///tmp/build/80754af9/tinycss_1617713798712/work
+tinycss2==1.2.1
+tldextract @ file:///opt/conda/conda-bld/tldextract_1646638314385/work
+tmdbv3api==1.7.7
+tokenizers==0.13.3
+toml @ file:///tmp/build/80754af9/toml_1616166611790/work
+tomli @ file:///tmp/build/80754af9/tomli_1637314251069/work
+toolz @ file:///tmp/build/80754af9/toolz_1636545406491/work
+torch==2.0.1
+tornado==6.2
+TPOT==0.11.7
+tqdm @ file:///C:/ci/tqdm_1650636210717/work
+traitlets==5.8.1
+transformers==4.29.2
+Twisted @ file:///C:/ci/twisted_1646835413846/work
+twisted-iocpsupport @ file:///C:/ci/twisted-iocpsupport_1646798932792/work
+typed-ast @ file:///C:/ci/typed-ast_1624953797214/work
+typeguard==2.13.3
+typer==0.7.0
+typesystem==0.3.0.dev0
+typing_extensions @ file:///opt/conda/conda-bld/typing_extensions_1647553014482/work
+tzdata==2022.5
+tzlocal==4.2
+ujson @ file:///C:/ci/ujson_1648044223886/work
+Unidecode @ file:///tmp/build/80754af9/unidecode_1614712377438/work
+update-checker==0.18.0
+urllib3==1.26.16
+uvicorn==0.13.1
+validators==0.20.0
+vega-datasets==0.9.0
+virtualenv==20.16.5
+visions==0.7.5
+voila==0.4.0
+w3lib @ file:///Users/ktietz/demo/mc3/conda-bld/w3lib_1629359764703/work
+wasabi==0.10.1
+watchdog @ file:///C:/ci/watchdog_1638367441841/work
+wcwidth @ file:///Users/ktietz/demo/mc3/conda-bld/wcwidth_1629357192024/work
+webencodings==0.5.1
+websocket-client @ file:///C:/ci/websocket-client_1614804375980/work
+websockets==10.4
+Werkzeug==2.2.3
+wget==3.2
+whitenoise==6.2.0
+widgetsnbextension @ file:///C:/ci/widgetsnbextension_1644991377168/work
+win-inet-pton @ file:///C:/ci/win_inet_pton_1605306162074/work
+win-unicode-console==0.5
+wincertstore==0.2
+wordcloud==1.8.2.2
+wrapt @ file:///C:/ci/wrapt_1607574570428/work
+xarray @ file:///opt/conda/conda-bld/xarray_1639166117697/work
+xgboost==1.7.4
+xlrd @ file:///tmp/build/80754af9/xlrd_1608072521494/work
+XlsxWriter @ file:///opt/conda/conda-bld/xlsxwriter_1649073856329/work
+xlwings==0.24.9
+xxhash==3.2.0
+yapf @ file:///tmp/build/80754af9/yapf_1615749224965/work
+yarl @ file:///C:/ci/yarl_1606940155993/work
+yellowbrick==1.5
+yfinance==0.1.87
+zict==2.0.0
+zipp @ file:///opt/conda/conda-bld/zipp_1641824620731/work
+zope.interface @ file:///C:/ci/zope.interface_1625036252485/work

request.py

@@ -0,0 +1,52 @@
+import requests
+
+url = "https://bloomberg-market-and-financial-news.p.rapidapi.com/market/auto-complete"
+
+##querystring = {"query":"infosys"}
+querystring = {"query":"company"}
+
+headers = {
+	"X-RapidAPI-Key": "ee0947a6afmshd9a0846869b0f80p12916fjsn610316852108",
+	"X-RapidAPI-Host": "bloomberg-market-and-financial-news.p.rapidapi.com"
+}
+
+response = requests.request("GET", url, headers=headers, params=querystring)
+
+
+print(response.text)
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+jsondata = response.json()
+print(jsondata)
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print(jsondata.keys())
+
+print(type(jsondata['quote']))
+print(type(jsondata['news']))
+import pandas as pd
+df = pd.DataFrame(jsondata['quote'])
+df2 = pd.DataFrame(jsondata['news'])
+print('***************************************************************************')
+print(df.info())
+print(df2.info())
+print('***************************************************************************')
+print(df.head(3))
+print(df2.head(3))
+print('***************************************************************************')
+print(df.shape)
+print(df2.shape)
+print('***************************************************************************')
+print(df.columns)
+print(df2.columns)
+print('***************************************************************************')
+df3 = pd.concat([df, df2], axis = 1)
+print(df3.columns)
+print(df3.shape)
+print('***************************************************************************')

request3.py

@@ -0,0 +1,42 @@
+import requests
+
+url = "https://text-analysis12.p.rapidapi.com/sentiment-analysis/api/v1.1"
+
+payload = {
+	"language": "english",
+	"text": "Falcon 9’s first stage has landed on the Of Course I Still Love You droneship – the 9th landing of this booster"
+}
+headers = {
+	"content-type": "application/json",
+	"X-RapidAPI-Key": "ee0947a6afmshd9a0846869b0f80p12916fjsn610316852108",
+	"X-RapidAPI-Host": "text-analysis12.p.rapidapi.com"
+}
+
+response = requests.request("POST", url, json=payload, headers=headers)
+
+print(response.text)
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+jsondata = response.json()
+print(jsondata)
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print(jsondata.keys())
+
+from pandas import json_normalize 
+import requests
+import json
+import pandas as pd
+textdata = json.loads(response.text)
+
+res = json_normalize(textdata)
+
+df = pd.DataFrame(res)
+print(df.shape)
+print(df.head(10))

requests2.py

@@ -0,0 +1,38 @@
+import requests
+
+url = "https://bloomberg-market-and-financial-news.p.rapidapi.com/news/list-by-region"
+
+querystring = {"id":"europe-home-v3"}
+
+headers = {
+	"X-RapidAPI-Key": "ee0947a6afmshd9a0846869b0f80p12916fjsn610316852108",
+	"X-RapidAPI-Host": "bloomberg-market-and-financial-news.p.rapidapi.com"
+}
+
+response = requests.request("GET", url, headers=headers, params=querystring)
+
+print(response.text)
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+jsondata = response.json()
+print(jsondata)
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print('***************************************************************************')
+print(jsondata.keys())
+
+from pandas import json_normalize 
+import requests
+import json
+import pandas as pd
+textdata = json.loads(response.text)
+
+res = json_normalize(textdata)
+
+df = pd.DataFrame(res)
+print(df.shape)

requirements.txt

@@ -0,0 +1,16 @@
+streamlit
+numpy>=1.13.3
+scikit-learn==0.20.3
+matplotlib>=1.4.3
+pandas>=0.19
+unidecode
+wordcloud
+scipy
+spacy==2.2.0
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.0/en_core_web_sm-2.2.0.tar.gz#egg=en_core_web_sm
+joblib
+xgboost
+plotly
+nltk
+
+

runtime.txt

@@ -0,0 +1 @@
+python-3.6.15

setup.sh

@@ -0,0 +1,13 @@
+mkdir -p ~/.streamlit/
+
+echo "\
+[general]\n\
+email = \"[email protected]\"\n\
+" > ~/.streamlit/credentials.toml
+
+echo "\
+[server]\n\
+headless = true\n\
+enableCORS=false\n\
+port = $PORT\n\
+" > ~/.streamlit/config.toml