nlp-menu 1.0.0__tar.gz

nlp_menu-1.0.0/PKG-INFO

@@ -0,0 +1,87 @@
+Metadata-Version: 2.4
+Name: nlp-menu
+Version: 1.0.0
+Summary: A collection of 10 NLP programs accessible via an interactive CLI menu
+License: MIT
+Keywords: nlp,word2vec,glove,transformers,cohere,spacy,menu
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: gensim
+Requires-Dist: matplotlib
+Requires-Dist: scikit-learn
+Requires-Dist: nltk
+Requires-Dist: cohere
+Requires-Dist: transformers
+Requires-Dist: torch
+Requires-Dist: langchain
+Requires-Dist: langchain-community
+Requires-Dist: langchain-cohere
+Requires-Dist: langchain-core
+Requires-Dist: pydantic
+Requires-Dist: wikipedia-api
+Requires-Dist: spacy
+
+# nlp-menu
+
+An interactive CLI menu for 10 NLP programs covering word embeddings, sentiment analysis, summarization, and more.
+
+## Installation
+
+```bash
+pip install nlp-menu
+```
+
+After installing the spaCy model (required for Program 10):
+
+```bash
+python -m spacy download en_core_web_sm
+```
+
+## Usage
+
+```bash
+nlp-menu
+```
+
+This launches an interactive menu:
+
+```
+╔══════════════════════════════════════════════════════╗
+║              🧠  NLP PROGRAMS MENU  🧠               ║
+╠══════════════════════════════════════════════════════╣
+║  1. GloVe Word Analogies (King-Man+Woman...)         ║
+║  2. Word Embedding PCA Visualization (Sports)        ║
+║  3. Word2Vec on Medical Corpus + PCA Plot            ║
+║  4. Prompt Enrichment with GloVe + Cohere            ║
+║  5. Paragraph Generator with GloVe + Cohere          ║
+║  6. Sentiment Analysis (Transformers)                ║
+║  7. Text Summarization (Pegasus)                     ║
+║  8. LangChain + Cohere File Summarizer               ║
+║  9. Institution Details via Wikipedia + Pydantic     ║
+║  10. IPC Chatbot (spaCy NER)                         ║
+║  0. Exit                                             ║
+╚══════════════════════════════════════════════════════╝
+```
+
+## Programs Overview
+
+| # | Program | Libraries Used |
+|---|---------|---------------|
+| 1 | GloVe Word Analogies | gensim |
+| 2 | Word Embedding PCA Visualization | gensim, matplotlib, scikit-learn |
+| 3 | Word2Vec Medical Corpus | gensim, nltk, matplotlib |
+| 4 | Prompt Enrichment | gensim, nltk, cohere |
+| 5 | Paragraph Generator | gensim, cohere |
+| 6 | Sentiment Analysis | transformers |
+| 7 | Text Summarization | transformers |
+| 8 | LangChain Summarizer | langchain, cohere |
+| 9 | Institution Scraper | wikipedia-api, pydantic |
+| 10 | IPC Chatbot | spacy |
+
+## License
+
+MIT

nlp_menu-1.0.0/README.md

@@ -0,0 +1,60 @@
+# nlp-menu
+
+An interactive CLI menu for 10 NLP programs covering word embeddings, sentiment analysis, summarization, and more.
+
+## Installation
+
+```bash
+pip install nlp-menu
+```
+
+After installing the spaCy model (required for Program 10):
+
+```bash
+python -m spacy download en_core_web_sm
+```
+
+## Usage
+
+```bash
+nlp-menu
+```
+
+This launches an interactive menu:
+
+```
+╔══════════════════════════════════════════════════════╗
+║              🧠  NLP PROGRAMS MENU  🧠               ║
+╠══════════════════════════════════════════════════════╣
+║  1. GloVe Word Analogies (King-Man+Woman...)         ║
+║  2. Word Embedding PCA Visualization (Sports)        ║
+║  3. Word2Vec on Medical Corpus + PCA Plot            ║
+║  4. Prompt Enrichment with GloVe + Cohere            ║
+║  5. Paragraph Generator with GloVe + Cohere          ║
+║  6. Sentiment Analysis (Transformers)                ║
+║  7. Text Summarization (Pegasus)                     ║
+║  8. LangChain + Cohere File Summarizer               ║
+║  9. Institution Details via Wikipedia + Pydantic     ║
+║  10. IPC Chatbot (spaCy NER)                         ║
+║  0. Exit                                             ║
+╚══════════════════════════════════════════════════════╝
+```
+
+## Programs Overview
+
+| # | Program | Libraries Used |
+|---|---------|---------------|
+| 1 | GloVe Word Analogies | gensim |
+| 2 | Word Embedding PCA Visualization | gensim, matplotlib, scikit-learn |
+| 3 | Word2Vec Medical Corpus | gensim, nltk, matplotlib |
+| 4 | Prompt Enrichment | gensim, nltk, cohere |
+| 5 | Paragraph Generator | gensim, cohere |
+| 6 | Sentiment Analysis | transformers |
+| 7 | Text Summarization | transformers |
+| 8 | LangChain Summarizer | langchain, cohere |
+| 9 | Institution Scraper | wikipedia-api, pydantic |
+| 10 | IPC Chatbot | spacy |
+
+## License
+
+MIT

nlp_menu-1.0.0/nlp_menu/__init__.py

@@ -0,0 +1,3 @@
+"""NLP Menu - A collection of 10 NLP programs accessible via CLI menu."""
+
+__version__ = "1.0.0"

nlp_menu-1.0.0/nlp_menu/cli.py

@@ -0,0 +1,65 @@
+"""NLP Menu - Interactive CLI menu for 10 NLP programs."""
+
+MENU = """
+╔══════════════════════════════════════════════════════╗
+║              🧠  NLP PROGRAMS MENU  🧠               ║
+╠══════════════════════════════════════════════════════╣
+║  1. GloVe Word Analogies (King-Man+Woman...)         ║
+║  2. Word Embedding PCA Visualization (Sports)        ║
+║  3. Word2Vec on Medical Corpus + PCA Plot            ║
+║  4. Prompt Enrichment with GloVe + Cohere            ║
+║  5. Paragraph Generator with GloVe + Cohere          ║
+║  6. Sentiment Analysis (Transformers)                ║
+║  7. Text Summarization (Pegasus)                     ║
+║  8. LangChain + Cohere File Summarizer               ║
+║  9. Institution Details via Wikipedia + Pydantic     ║
+║  10. IPC Chatbot (spaCy NER)                         ║
+║  0. Exit                                             ║
+╚══════════════════════════════════════════════════════╝
+"""
+
+def main():
+    while True:
+        print(MENU)
+        choice = input("Enter program number (0 to exit): ").strip()
+
+        if choice == "0":
+            print("👋 Goodbye!")
+            break
+        elif choice == "1":
+            from nlp_menu import program1
+            program1.run()
+        elif choice == "2":
+            from nlp_menu import program2
+            program2.run()
+        elif choice == "3":
+            from nlp_menu import program3
+            program3.run()
+        elif choice == "4":
+            from nlp_menu import program4
+            program4.run()
+        elif choice == "5":
+            from nlp_menu import program5
+            program5.run()
+        elif choice == "6":
+            from nlp_menu import program6
+            program6.run()
+        elif choice == "7":
+            from nlp_menu import program7
+            program7.run()
+        elif choice == "8":
+            from nlp_menu import program8
+            program8.run()
+        elif choice == "9":
+            from nlp_menu import program9
+            program9.run()
+        elif choice == "10":
+            from nlp_menu import program10
+            program10.run()
+        else:
+            print("❌ Invalid choice. Please enter a number between 0 and 10.")
+
+        input("\n[Press Enter to return to menu...]")
+
+if __name__ == "__main__":
+    main()

nlp_menu-1.0.0/nlp_menu/program1.py

@@ -0,0 +1,31 @@
+import gensim.downloader as api
+
+def run():
+    # Load GloVe model
+    model = api.load("glove-wiki-gigaword-50")
+
+    # Example 1: King - Man + Woman
+    result = model.most_similar(
+        positive=['king', 'woman'],
+        negative=['man'],
+        topn=1
+    )
+    print("King - Man + Woman =", result[0][0])
+    print("Similarity:", result[0][1])
+
+    # Example 2: Paris - France + Italy
+    result = model.most_similar(
+        positive=['paris', 'italy'],
+        negative=['france'],
+        topn=1
+    )
+    print("Paris - France + Italy =", result[0][0])
+    print("Similarity:", result[0][1])
+
+    # Example 3: Similar words to programming
+    result = model.most_similar(
+        positive=['programming'],
+        topn=5
+    )
+    for word, similarity in result:
+        print(word, similarity)

nlp_menu-1.0.0/nlp_menu/program10.py

@@ -0,0 +1,53 @@
+import spacy
+
+IPC_SECTIONS = {
+    "302": "Section 302 IPC: Punishment for murder. Whoever commits murder shall be punished with death, or imprisonment for life, and shall also be liable to fine.",
+    "375": "Section 375 IPC: Rape. This section defines what constitutes rape under Indian law.",
+    "420": "Section 420 IPC: Cheating and dishonestly inducing delivery of property.",
+    "376": "Section 376 IPC: Punishment for rape. Rigorous imprisonment of not less than 10 years, which may extend to life imprisonment, and a fine.",
+    "124a": "Section 124A IPC: Sedition – whoever, by words or signs, brings or attempts to bring hatred or contempt against the Government shall be punished."
+}
+
+def run():
+    nlp = spacy.load("en_core_web_sm")
+
+    def extract_ipc_section(user_input):
+        doc = nlp(user_input)
+        for i, token in enumerate(doc):
+            if token.like_num and token.text in IPC_SECTIONS:
+                return token.text
+            if "section" in token.text.lower():
+                if i + 1 < len(doc):
+                    next_token = doc[i + 1]
+                    if next_token.text in IPC_SECTIONS:
+                        return next_token.text
+        return None
+
+    def detect_intent(user_input):
+        if "section" in user_input.lower() or any(sec in user_input for sec in IPC_SECTIONS.keys()):
+            return "ipc_query"
+        elif "hello" in user_input.lower() or "hi" in user_input.lower():
+            return "greeting"
+        else:
+            return "general"
+
+    print("IPC Chatbot: Hello! Ask me about any section of the Indian Penal Code (e.g., 'What is Section 302?').")
+
+    while True:
+        user_input = input("You: ")
+        if user_input.lower() in ['exit', 'quit', 'bye']:
+            print("IPC Chatbot: Goodbye!")
+            break
+
+        intent = detect_intent(user_input)
+
+        if intent == "ipc_query":
+            section = extract_ipc_section(user_input)
+            if section:
+                print(f"IPC Chatbot: {IPC_SECTIONS[section]}")
+            else:
+                print("IPC Chatbot: Sorry, I couldn't identify the IPC section. Please specify like 'Section 302'.")
+        elif intent == "greeting":
+            print("IPC Chatbot: Hello! Ask me about any IPC section.")
+        else:
+            print("IPC Chatbot: I can help you with information about the Indian Penal Code. Try asking about a section like 'What is Section 420?'")

nlp_menu-1.0.0/nlp_menu/program2.py

@@ -0,0 +1,24 @@
+import matplotlib.pyplot as plt
+import gensim.downloader as api
+from sklearn.decomposition import PCA
+
+def run():
+    model = api.load("glove-wiki-gigaword-50")
+
+    words = ["football", "cricket", "volleyball", "kabaddi", "basketball"]
+    embeddings = [model[word] for word in words]
+
+    pca = PCA(n_components=2)
+    reduced = pca.fit_transform(embeddings)
+
+    plt.figure(figsize=(12, 8))
+    for i, word in enumerate(words):
+        x, y = reduced[i]
+        plt.scatter(x, y)
+        plt.text(x + 0.02, y + 0.02, word)
+
+    plt.title("2D Visualization of Word Embeddings")
+    plt.xlabel("PCA Component 1")
+    plt.ylabel("PCA Component 2")
+    plt.grid(True)
+    plt.show()

nlp_menu-1.0.0/nlp_menu/program3.py

@@ -0,0 +1,63 @@
+import nltk
+import string
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from gensim.models import Word2Vec
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+
+def run():
+    medical_corpus = [
+        "Diabetes is a chronic disease that affects the way the body process blood sugar.",
+        "Hypertension, or high blood pressure, can lead to heart disease and stroke.",
+        "The patient was diagnosed with pneumonia and prescribed antibiotics.",
+        "Insulin therapy is commonly used for type 1 diabetes patient.",
+        "Cardiovascular diseases are leading cause of death worldwide."
+    ]
+
+    nltk.download('punkt', quiet=True)
+    nltk.download('stopwords', quiet=True)
+
+    stop_words = set(stopwords.words("english"))
+    processed_corpus = []
+
+    for sentence in medical_corpus:
+        tokens = word_tokenize(sentence.lower())
+        tokens = [word for word in tokens if word not in stop_words and word not in string.punctuation]
+        processed_corpus.append(tokens)
+
+    print("Processed corpus:", processed_corpus)
+
+    word2vec_model = Word2Vec(
+        sentences=processed_corpus,
+        vector_size=100,
+        window=5,
+        min_count=1,
+        workers=4
+    )
+
+    word2vec_model.save("medical_word2vec.model")
+    word2vec_model = Word2Vec.load("medical_word2vec.model")
+
+    print("Vocabulary:", list(word2vec_model.wv.index_to_key))
+    print("Similar words to 'diabetes':", word2vec_model.wv.most_similar("diabetes"))
+
+    result = word2vec_model.wv.most_similar(
+        positive=['hypertension', 'heart'],
+        negative=['stroke']
+    )
+    print("Word vector arithmetic result:", result)
+
+    words = list(word2vec_model.wv.index_to_key)
+    word_vectors = [word2vec_model.wv[word] for word in words]
+
+    pca = PCA(n_components=2)
+    reduced_vectors = pca.fit_transform(word_vectors)
+
+    plt.figure(figsize=(8, 6))
+    for i, word in enumerate(words):
+        plt.scatter(reduced_vectors[i, 0], reduced_vectors[i, 1])
+        plt.annotate(word, (reduced_vectors[i, 0], reduced_vectors[i, 1]))
+
+    plt.title("Word Embedding Visualization (PCA)")
+    plt.show()

nlp_menu-1.0.0/nlp_menu/program4.py

@@ -0,0 +1,76 @@
+import ssl
+import nltk
+import string
+import cohere
+from gensim.downloader import load
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+
+def run():
+    ssl._create_default_https_context = ssl._create_unverified_context
+    nltk.download('punkt', quiet=True)
+    nltk.download('averaged_perceptron_tagger', quiet=True)
+    nltk.download('stopwords', quiet=True)
+
+    print("Loading GloVe model...")
+    embedding_model = load("glove-wiki-gigaword-50")
+    print("GloVe loaded!")
+
+    def clean_text(text):
+        text = text.lower()
+        text = text.translate(str.maketrans(' ', ' ', string.punctuation))
+        return text
+
+    def extract_keywords(text, top_pos_tags=['NN', 'NNS', 'JJ', 'VB']):
+        tokens = word_tokenize(text)
+        tokens = [t for t in tokens if t not in stopwords.words('english')]
+        pos_tags = nltk.pos_tag(tokens)
+        keywords = [word for word, tag in pos_tags if tag in top_pos_tags]
+        return list(set(keywords))
+
+    def get_similar_words(word, top_n=3):
+        try:
+            return [w for w, _ in embedding_model.most_similar(word, topn=top_n)]
+        except KeyError:
+            return []
+
+    def enrich_prompt(prompt, top_n=3):
+        cleaned_prompt = clean_text(prompt)
+        keywords = extract_keywords(cleaned_prompt)
+        enriched_prompt = prompt
+        for word in keywords:
+            similar_words = get_similar_words(word, top_n)
+            if similar_words:
+                enriched_prompt += " " + " ".join(similar_words)
+        return enriched_prompt
+
+    api_key = input("Enter your Cohere API key: ")
+    co = cohere.Client(api_key)
+
+    original_prompt = input("Enter your prompt: ")
+    enriched_prompt = enrich_prompt(original_prompt)
+
+    print("\n Original Prompt:\n", original_prompt)
+    print("\n Enriched Prompt:\n", enriched_prompt)
+
+    def generate_response(prompt_text, creative=True):
+        if creative:
+            prompt_text = "write a detailed and imaginative story based on following prompt:\n" + prompt_text
+        response = co.chat(model="command-a-03-2025", message=prompt_text)
+        return response.text
+
+    response_original = generate_response(original_prompt, creative=True)
+    response_enriched = generate_response(enriched_prompt, creative=True)
+
+    print("\n\n ===Response to original prompt\n")
+    print(response_original)
+    print("\n\n ===Response to enriched prompt\n")
+    print(response_enriched)
+
+    print("\n\n===Comparison===\n")
+    print("""
+1. Detail: Enriched prompt should produce longer, more descriptive output.
+2. Vocabulary: Enriched prompt uses richer wording from similar words.
+3. Context relevance: Enriched prompt guides the AI to cover more specific concepts.
+4. Creativity: Enriched prompt usually results in more imaginative storytelling.
+""")

nlp_menu-1.0.0/nlp_menu/program5.py

@@ -0,0 +1,36 @@
+import cohere
+from gensim.downloader import load
+
+def run():
+    print("Loading pre-trained GloVe model...")
+    model = load("glove-wiki-gigaword-50")
+    print("Model loaded successfully!")
+
+    api_key = input("Enter your Cohere API key: ")
+    co = cohere.Client(api_key)
+
+    def generate_para(seed_word, words):
+        words_str = ", ".join(words)
+        prompt = (
+            f"Write a meaningful and well structured paragraph about '{seed_word}'."
+            f" Use these related words naturally: {words_str}."
+        )
+        try:
+            response = co.chat(model='command-a-03-2025', message=prompt)
+            return response.text.strip()
+        except Exception as e:
+            return f"Cohere API error: {e}"
+
+    seed_word = input("Enter a seed word: ").lower()
+
+    if seed_word not in model.key_to_index:
+        print("Word not in vocabulary.")
+    else:
+        similar_words = model.most_similar(seed_word, topn=10)
+        words = [word for word, score in similar_words]
+        print("10 similar words found:")
+        print(", ".join(words), "\n")
+
+        paragraph = generate_para(seed_word, words)
+        print("Generated paragraph:\n")
+        print(paragraph)

nlp_menu-1.0.0/nlp_menu/program6.py

@@ -0,0 +1,17 @@
+from transformers import pipeline
+
+def run():
+    sentiment_analyzer = pipeline("sentiment-analysis")
+
+    def analyze_sentiment(text):
+        result = sentiment_analyzer(text)
+        label = result[0]["label"]
+        score = result[0]["score"]
+        return f"Sentiment: {label} (Confidence: {score:.2f})"
+
+    while True:
+        user_input = input("Enter sentence (or 'exit'): ").strip()
+        if user_input.lower() == "exit":
+            print("Exiting...")
+            break
+        print(analyze_sentiment(user_input))

nlp_menu-1.0.0/nlp_menu/program7.py

@@ -0,0 +1,15 @@
+from transformers import pipeline
+
+def run():
+    print("Loading summarization model...")
+    summarizer = pipeline("summarization", model="google/pegasus-arxiv")
+
+    text = input("\nEnter the text you want to summarize:\n").strip()
+
+    if len(text.split()) < 30:
+        print("Text too short to summarize.")
+    else:
+        text = "Summarize this text in simple words:\n" + text
+        summary = summarizer(text, max_length=60, min_length=25, do_sample=False)
+        print("\nSummarized Text:")
+        print(summary[0]['summary_text'])

nlp_menu-1.0.0/nlp_menu/program8.py

@@ -0,0 +1,22 @@
+from langchain_core.prompts import PromptTemplate
+from langchain_cohere import ChatCohere
+
+def run():
+    api_key = input("Enter your Cohere API key: ").strip()
+    file_path = input("Enter the path to your text file: ").strip()
+
+    with open(file_path, "r", encoding="utf-8") as file:
+        text = file.read()
+
+    print("File loaded successfully!")
+
+    prompt = PromptTemplate(
+        input_variables=["text"],
+        template="Summarize the following text in simple words:\n\n{text}"
+    )
+
+    llm = ChatCohere(cohere_api_key=api_key)
+    result = llm.invoke(prompt.format(text=text))
+
+    print("\nSummary:\n")
+    print(result.content)

nlp_menu-1.0.0/nlp_menu/program9.py

@@ -0,0 +1,43 @@
+from pydantic import BaseModel
+import wikipediaapi
+import re
+
+class InstitutionDetails(BaseModel):
+    name: str
+    founder: str
+    founded_year: str
+    branches: str
+    employees: str
+    summary: str
+
+def run():
+    def fetch_details(name):
+        wiki = wikipediaapi.Wikipedia(
+            user_agent="InstitutionScraper/1.0 (student project; contact: your_email@example.com)",
+            language="en"
+        )
+        page = wiki.page(name)
+
+        if not page.exists():
+            raise ValueError("Institution not found")
+
+        text = page.text.lower()
+        founder = re.search(r"founded by ([^.]+)", text)
+        year = re.search(r"(founded|established) in (\d{4})", text)
+        employees = re.search(r"(\d+[,\d]*) employees", text)
+
+        return InstitutionDetails(
+            name=name,
+            founder=founder.group(1) if founder else "Not Available",
+            founded_year=year.group(2) if year else "Not Available",
+            branches="Multiple branches",
+            employees=employees.group(1) if employees else "Not Available",
+            summary=" ".join(page.summary.split(".")[:4]) + "."
+        )
+
+    name = input("Enter Institution Name: ")
+    try:
+        result = fetch_details(name)
+        print(result.model_dump_json(indent=4))
+    except ValueError as e:
+        print(e)

nlp_menu-1.0.0/nlp_menu.egg-info/PKG-INFO

@@ -0,0 +1,87 @@
+Metadata-Version: 2.4
+Name: nlp-menu
+Version: 1.0.0
+Summary: A collection of 10 NLP programs accessible via an interactive CLI menu
+License: MIT
+Keywords: nlp,word2vec,glove,transformers,cohere,spacy,menu
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: gensim
+Requires-Dist: matplotlib
+Requires-Dist: scikit-learn
+Requires-Dist: nltk
+Requires-Dist: cohere
+Requires-Dist: transformers
+Requires-Dist: torch
+Requires-Dist: langchain
+Requires-Dist: langchain-community
+Requires-Dist: langchain-cohere
+Requires-Dist: langchain-core
+Requires-Dist: pydantic
+Requires-Dist: wikipedia-api
+Requires-Dist: spacy
+
+# nlp-menu
+
+An interactive CLI menu for 10 NLP programs covering word embeddings, sentiment analysis, summarization, and more.
+
+## Installation
+
+```bash
+pip install nlp-menu
+```
+
+After installing the spaCy model (required for Program 10):
+
+```bash
+python -m spacy download en_core_web_sm
+```
+
+## Usage
+
+```bash
+nlp-menu
+```
+
+This launches an interactive menu:
+
+```
+╔══════════════════════════════════════════════════════╗
+║              🧠  NLP PROGRAMS MENU  🧠               ║
+╠══════════════════════════════════════════════════════╣
+║  1. GloVe Word Analogies (King-Man+Woman...)         ║
+║  2. Word Embedding PCA Visualization (Sports)        ║
+║  3. Word2Vec on Medical Corpus + PCA Plot            ║
+║  4. Prompt Enrichment with GloVe + Cohere            ║
+║  5. Paragraph Generator with GloVe + Cohere          ║
+║  6. Sentiment Analysis (Transformers)                ║
+║  7. Text Summarization (Pegasus)                     ║
+║  8. LangChain + Cohere File Summarizer               ║
+║  9. Institution Details via Wikipedia + Pydantic     ║
+║  10. IPC Chatbot (spaCy NER)                         ║
+║  0. Exit                                             ║
+╚══════════════════════════════════════════════════════╝
+```
+
+## Programs Overview
+
+| # | Program | Libraries Used |
+|---|---------|---------------|
+| 1 | GloVe Word Analogies | gensim |
+| 2 | Word Embedding PCA Visualization | gensim, matplotlib, scikit-learn |
+| 3 | Word2Vec Medical Corpus | gensim, nltk, matplotlib |
+| 4 | Prompt Enrichment | gensim, nltk, cohere |
+| 5 | Paragraph Generator | gensim, cohere |
+| 6 | Sentiment Analysis | transformers |
+| 7 | Text Summarization | transformers |
+| 8 | LangChain Summarizer | langchain, cohere |
+| 9 | Institution Scraper | wikipedia-api, pydantic |
+| 10 | IPC Chatbot | spacy |
+
+## License
+
+MIT

nlp_menu-1.0.0/nlp_menu.egg-info/SOURCES.txt

@@ -0,0 +1,20 @@
+README.md
+pyproject.toml
+nlp_menu/__init__.py
+nlp_menu/cli.py
+nlp_menu/program1.py
+nlp_menu/program10.py
+nlp_menu/program2.py
+nlp_menu/program3.py
+nlp_menu/program4.py
+nlp_menu/program5.py
+nlp_menu/program6.py
+nlp_menu/program7.py
+nlp_menu/program8.py
+nlp_menu/program9.py
+nlp_menu.egg-info/PKG-INFO
+nlp_menu.egg-info/SOURCES.txt
+nlp_menu.egg-info/dependency_links.txt
+nlp_menu.egg-info/entry_points.txt
+nlp_menu.egg-info/requires.txt
+nlp_menu.egg-info/top_level.txt

nlp_menu-1.0.0/nlp_menu.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

nlp_menu-1.0.0/nlp_menu.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+nlp-menu = nlp_menu.cli:main

nlp_menu-1.0.0/nlp_menu.egg-info/requires.txt

@@ -0,0 +1,14 @@
+gensim
+matplotlib
+scikit-learn
+nltk
+cohere
+transformers
+torch
+langchain
+langchain-community
+langchain-cohere
+langchain-core
+pydantic
+wikipedia-api
+spacy

nlp_menu-1.0.0/nlp_menu.egg-info/top_level.txt

@@ -0,0 +1 @@
+nlp_menu

nlp_menu-1.0.0/pyproject.toml

@@ -0,0 +1,41 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "nlp-menu"
+version = "1.0.0"
+description = "A collection of 10 NLP programs accessible via an interactive CLI menu"
+readme = "README.md"
+requires-python = ">=3.8"
+license = { text = "MIT" }
+keywords = ["nlp", "word2vec", "glove", "transformers", "cohere", "spacy", "menu"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "gensim",
+    "matplotlib",
+    "scikit-learn",
+    "nltk",
+    "cohere",
+    "transformers",
+    "torch",
+    "langchain",
+    "langchain-community",
+    "langchain-cohere",
+    "langchain-core",
+    "pydantic",
+    "wikipedia-api",
+    "spacy",
+]
+
+[project.scripts]
+nlp-menu = "nlp_menu.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["nlp_menu*"]

nlp_menu-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+