hinglish-nlp 0.2.0__tar.gz

hinglish_nlp-0.2.0/PKG-INFO

@@ -0,0 +1,178 @@
+Metadata-Version: 2.4
+Name: hinglish-nlp
+Version: 0.2.0
+Summary: Hinglish (Roman Hindi + English) NLP toolkit - Sentiment, Emotion, Sarcasm & more
+Author-email: Lalit <official.lalitpal08@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/Lalit2206/hinglish-nlp
+Project-URL: Repository, https://github.com/Lalit2206/hinglish-nlp
+Keywords: hinglish,nlp,sentiment,hindi,roman-hindi,text-analysis
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Natural Language :: Hindi
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic>=2.0
+
+# hinglish-nlp 🇮🇳
+
+A powerful NLP toolkit for **Hinglish** (Roman Hindi + English) text analysis.
+
+[![PyPI version](https://badge.fury.io/py/hinglish-nlp.svg)](https://badge.fury.io/py/hinglish-nlp)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+---
+
+## Installation
+
+```bash
+pip install hinglish-nlp
+```
+
+---
+
+## Features
+
+| Feature | Description |
+|--------|-------------|
+| ✅ Sentiment Analysis | Positive / Negative / Neutral / Mixed |
+| ✅ Emotion Detection | Joy, Anger, Sadness, Fear, Surprise, Disgust |
+| ✅ Sarcasm Detection | Pattern + contradiction based |
+| ✅ Language Mix Detection | Hinglish vs English ratio |
+| ✅ Transliteration | Roman Hindi → Devanagari |
+| ✅ Batch Processing | Multiple texts at once |
+| ✅ Key Phrase Extraction | Important phrases from text |
+| ✅ Intensity Score | 0.0 to 1.0 scale |
+| ✅ Confidence Score | How sure the model is |
+
+---
+
+## Usage
+
+### Basic Sentiment Analysis
+```python
+from hinglish import analyze
+
+result = analyze("yaar bahut mast movie thi!")
+print(result["mood"])        # positive
+print(result["emoji"])       # 😊
+print(result["intensity"])   # 0.45
+print(result["confidence"])  # 0.75
+```
+
+### Emotion Detection
+```python
+from hinglish import detect_emotion
+
+emotions = detect_emotion("mujhe bahut gussa aa raha hai!")
+print(emotions)  # {'anger': 0.35}
+
+emotions = detect_emotion("aaj bahut khushi hui yaar!")
+print(emotions)  # {'joy': 0.7}
+```
+
+### Sarcasm Detection
+```python
+from hinglish import is_sarcastic
+
+result = is_sarcastic("haan bilkul, bahut accha hai na!!")
+print(result)
+# {'is_sarcastic': True, 'confidence': 0.6}
+```
+
+### Language Mix Detection
+```python
+from hinglish import detect_language
+
+mix = detect_language("yaar ye movie bahut boring thi")
+print(mix)
+# {'hinglish': 0.5, 'english': 0.33, 'unknown': 0.17}
+```
+
+### Transliteration (Roman → Devanagari)
+```python
+from hinglish import transliterate
+
+text = transliterate("mera naam lalit hai")
+print(text)  # मेरा नाम ललित है
+```
+
+### Batch Processing
+```python
+from hinglish import analyze_batch
+
+texts = [
+    "yaar mast movie thi!",
+    "bilkul bakwaas tha yaar",
+    "theek thak tha, kuch khaas nahi"
+]
+
+results = analyze_batch(texts)
+for r in results:
+    print(r["mood"], r["emoji"])
+# positive 😊
+# negative 😠
+# neutral  😐
+```
+
+### Full Analysis
+```python
+from hinglish import analyze
+
+result = analyze("Phone ki battery toh bekar hai but camera mast hai")
+print(result)
+# {
+#   'mood': 'mixed',
+#   'intensity': 0.3,
+#   'confidence': 0.75,
+#   'emoji': '🤨',
+#   'sentiment': 'mixed',
+#   'key_phrases': ['Phone ki battery toh bekar hai but camera mast hai'],
+#   'sarcasm': False,
+#   'sarcasm_confidence': 0.0,
+#   'language_mix': {'hinglish': 0.36, 'english': 0.55, 'unknown': 0.09},
+#   'category': 'mixed',
+#   'summary': 'A detailed Hinglish message expressing mixed sentiment...',
+#   'emotions': {'disgust': 0.35},
+#   'word_count': 11,
+#   'positive_words_found': ['mast'],
+#   'negative_words_found': ['bekar'],
+#   'transliteration': 'Phone की battery तो bekar है but camera मस्त है'
+# }
+```
+
+---
+
+## Output Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `mood` | str | positive / negative / neutral / mixed |
+| `intensity` | float | 0.0 – 1.0 |
+| `confidence` | float | 0.0 – 1.0 |
+| `emoji` | str | Visual mood indicator |
+| `sentiment` | str | Same as mood |
+| `key_phrases` | list | Important phrases |
+| `sarcasm` | bool | Is text sarcastic? |
+| `sarcasm_confidence` | float | Sarcasm confidence score |
+| `language_mix` | dict | hinglish / english / unknown ratio |
+| `category` | str | praise / complaint / casual / mixed |
+| `summary` | str | Short summary of the text |
+| `emotions` | dict | Detected emotions with scores |
+| `word_count` | int | Total word count |
+| `positive_words_found` | list | Positive words detected |
+| `negative_words_found` | list | Negative words detected |
+| `transliteration` | str | Roman → Devanagari |
+
+---
+
+## Author
+
+**Lalit** — [lalitpal2206](https://pypi.org/user/lalitpal2206/)
+
+## License
+
+MIT License

hinglish_nlp-0.2.0/README.md

@@ -0,0 +1,160 @@
+# hinglish-nlp 🇮🇳
+
+A powerful NLP toolkit for **Hinglish** (Roman Hindi + English) text analysis.
+
+[![PyPI version](https://badge.fury.io/py/hinglish-nlp.svg)](https://badge.fury.io/py/hinglish-nlp)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+---
+
+## Installation
+
+```bash
+pip install hinglish-nlp
+```
+
+---
+
+## Features
+
+| Feature | Description |
+|--------|-------------|
+| ✅ Sentiment Analysis | Positive / Negative / Neutral / Mixed |
+| ✅ Emotion Detection | Joy, Anger, Sadness, Fear, Surprise, Disgust |
+| ✅ Sarcasm Detection | Pattern + contradiction based |
+| ✅ Language Mix Detection | Hinglish vs English ratio |
+| ✅ Transliteration | Roman Hindi → Devanagari |
+| ✅ Batch Processing | Multiple texts at once |
+| ✅ Key Phrase Extraction | Important phrases from text |
+| ✅ Intensity Score | 0.0 to 1.0 scale |
+| ✅ Confidence Score | How sure the model is |
+
+---
+
+## Usage
+
+### Basic Sentiment Analysis
+```python
+from hinglish import analyze
+
+result = analyze("yaar bahut mast movie thi!")
+print(result["mood"])        # positive
+print(result["emoji"])       # 😊
+print(result["intensity"])   # 0.45
+print(result["confidence"])  # 0.75
+```
+
+### Emotion Detection
+```python
+from hinglish import detect_emotion
+
+emotions = detect_emotion("mujhe bahut gussa aa raha hai!")
+print(emotions)  # {'anger': 0.35}
+
+emotions = detect_emotion("aaj bahut khushi hui yaar!")
+print(emotions)  # {'joy': 0.7}
+```
+
+### Sarcasm Detection
+```python
+from hinglish import is_sarcastic
+
+result = is_sarcastic("haan bilkul, bahut accha hai na!!")
+print(result)
+# {'is_sarcastic': True, 'confidence': 0.6}
+```
+
+### Language Mix Detection
+```python
+from hinglish import detect_language
+
+mix = detect_language("yaar ye movie bahut boring thi")
+print(mix)
+# {'hinglish': 0.5, 'english': 0.33, 'unknown': 0.17}
+```
+
+### Transliteration (Roman → Devanagari)
+```python
+from hinglish import transliterate
+
+text = transliterate("mera naam lalit hai")
+print(text)  # मेरा नाम ललित है
+```
+
+### Batch Processing
+```python
+from hinglish import analyze_batch
+
+texts = [
+    "yaar mast movie thi!",
+    "bilkul bakwaas tha yaar",
+    "theek thak tha, kuch khaas nahi"
+]
+
+results = analyze_batch(texts)
+for r in results:
+    print(r["mood"], r["emoji"])
+# positive 😊
+# negative 😠
+# neutral  😐
+```
+
+### Full Analysis
+```python
+from hinglish import analyze
+
+result = analyze("Phone ki battery toh bekar hai but camera mast hai")
+print(result)
+# {
+#   'mood': 'mixed',
+#   'intensity': 0.3,
+#   'confidence': 0.75,
+#   'emoji': '🤨',
+#   'sentiment': 'mixed',
+#   'key_phrases': ['Phone ki battery toh bekar hai but camera mast hai'],
+#   'sarcasm': False,
+#   'sarcasm_confidence': 0.0,
+#   'language_mix': {'hinglish': 0.36, 'english': 0.55, 'unknown': 0.09},
+#   'category': 'mixed',
+#   'summary': 'A detailed Hinglish message expressing mixed sentiment...',
+#   'emotions': {'disgust': 0.35},
+#   'word_count': 11,
+#   'positive_words_found': ['mast'],
+#   'negative_words_found': ['bekar'],
+#   'transliteration': 'Phone की battery तो bekar है but camera मस्त है'
+# }
+```
+
+---
+
+## Output Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `mood` | str | positive / negative / neutral / mixed |
+| `intensity` | float | 0.0 – 1.0 |
+| `confidence` | float | 0.0 – 1.0 |
+| `emoji` | str | Visual mood indicator |
+| `sentiment` | str | Same as mood |
+| `key_phrases` | list | Important phrases |
+| `sarcasm` | bool | Is text sarcastic? |
+| `sarcasm_confidence` | float | Sarcasm confidence score |
+| `language_mix` | dict | hinglish / english / unknown ratio |
+| `category` | str | praise / complaint / casual / mixed |
+| `summary` | str | Short summary of the text |
+| `emotions` | dict | Detected emotions with scores |
+| `word_count` | int | Total word count |
+| `positive_words_found` | list | Positive words detected |
+| `negative_words_found` | list | Negative words detected |
+| `transliteration` | str | Roman → Devanagari |
+
+---
+
+## Author
+
+**Lalit** — [lalitpal2206](https://pypi.org/user/lalitpal2206/)
+
+## License
+
+MIT License

hinglish_nlp-0.2.0/hinglish/__init__.py

@@ -0,0 +1,38 @@
+"""
+hinglish-nlp
+============
+A powerful NLP toolkit for Hinglish (Roman Hindi + English) text analysis.
+
+Quick start
+-----------
+>>> from hinglish import analyze
+>>> result = analyze("yaar bahut mast movie thi!")
+>>> print(result["mood"])       # positive
+>>> print(result["emotions"])   # {'joy': 0.35}
+
+>>> from hinglish import analyze_batch, transliterate, detect_emotion
+"""
+
+from .analyzer import (
+    analyze,
+    analyze_batch,
+    transliterate,
+    detect_language,
+    detect_emotion,
+    is_sarcastic,
+    HinglishAnalysis,
+    HinglishAnalyzer,
+)
+
+__version__ = "0.2.0"
+__author__ = "Lalit"
+__all__ = [
+    "analyze",
+    "analyze_batch",
+    "transliterate",
+    "detect_language",
+    "detect_emotion",
+    "is_sarcastic",
+    "HinglishAnalysis",
+    "HinglishAnalyzer",
+]

hinglish_nlp-0.2.0/hinglish/analyzer.py

@@ -0,0 +1,368 @@
+from dataclasses import dataclass, field
+from typing import Dict, List, Any, Optional
+import re
+
+
+#  LEXICON
+POSITIVE_WORDS = {
+    # General positive
+    "mast", "badiya", "zabardast", "awesome", "superb", "love", "best",
+    "perfect", "great", "achha", "accha", "nice", "kamaal", "shandaar",
+    "dhamaka", "bindaas", "jhakaas", "wah", "waah", "solid", "killer",
+    "dope", "lit", "fire", "too good", "ekdum sahi", "full mast",
+    "khush", "khushi", "maza", "party", "celebrate", "lajawaab",
+    "shaandaar", "gazab", "jalwa", "badhiya", "outstanding", "excellent",
+    "wonderful", "fantastic", "brilliant", "amazing", "superb", "fabulous",
+    "incredible", "marvelous", "splendid", "terrific", "spectacular",
+    "magnificent", "glorious", "superb", "lovely", "beautiful", "gorgeous",
+    "stunning", "charming", "delightful", "enjoyable", "fun", "exciting",
+    "thrilling", "refreshing", "satisfying", "pleasing", "impressive",
+    "remarkable", "extraordinary", "phenomenal", "exceptional", "top",
+    "sahi", "bilkul sahi", "dum", "dum hai", "kya baat", "ekdum",
+    "maja", "maja aaya", "mst", "bdhiya", "zbrdsst", "kmaal",
+    "happy", "glad", "joyful", "cheerful", "content", "pleased",
+    "grateful", "thankful", "blessed", "fortunate", "lucky",
+    "proud", "confident", "hopeful", "optimistic", "positive",
+    "energetic", "enthusiastic", "passionate", "motivated", "inspired",
+    "relaxed", "peaceful", "calm", "comfortable", "satisfied",
+}
+
+NEGATIVE_WORDS = {
+    # General negative
+    "bakwaas", "bekar", "kharaab", "worst", "faltu", "garbage",
+    "disappoint", "boring", "time waste", "bekaar", "ganda", "bura",
+    "kharab", "wahiyat", "forma", "forma", "useless", "pathetic",
+    "terrible", "horrible", "awful", "dreadful", "atrocious", "abysmal",
+    "disgusting", "revolting", "repulsive", "nasty", "vile", "foul",
+    "lousy", "poor", "inferior", "substandard", "inadequate", "deficient",
+    "flawed", "faulty", "broken", "damaged", "ruined", "destroyed",
+    "failed", "failure", "disaster", "catastrophe", "tragedy", "mess",
+    "problem", "issue", "trouble", "difficulty", "challenge", "obstacle",
+    "frustrating", "annoying", "irritating", "aggravating", "infuriating",
+    "disappointing", "unsatisfying", "dissatisfying", "displeasing",
+    "sad", "unhappy", "miserable", "depressed", "gloomy", "melancholy",
+    "upset", "distressed", "troubled", "worried", "anxious", "stressed",
+    "angry", "furious", "enraged", "outraged", "livid", "irate",
+    "disgusted", "repelled", "appalled", "horrified", "shocked",
+    "bored", "dull", "tedious", "monotonous", "repetitive", "bland",
+    "nahi", "mat", "bandh", "band", "chup", "shut",
+}
+
+INTENSIFIERS = {
+    "bahut", "bohot", "bht", "very", "super", "ekdum", "bilkul",
+    "sabse", "itna", "utna", "kitna", "zyada", "boht", "bhot",
+    "extremely", "incredibly", "absolutely", "totally", "completely",
+    "utterly", "highly", "deeply", "strongly", "severely", "greatly",
+    "tremendously", "enormously", "immensely", "vastly", "profoundly",
+}
+
+EMOTION_LEXICON = {
+    "anger": {
+        "gussa", "ghussa", "pagal", "bakwas", "beizzati", "insult",
+        "angry", "furious", "rage", "mad", "irritated", "annoyed",
+        "frustrated", "outraged", "livid", "enraged", "irate",
+        "aggressive", "hostile", "violent", "hateful", "resentful",
+        "jalega", "jala", "jalao", "maar", "marunga", "toot",
+    },
+    "joy": {
+        "khushi", "maza", "party", "celebrate", "mast", "khush",
+        "happy", "joyful", "cheerful", "delighted", "elated", "ecstatic",
+        "thrilled", "excited", "glad", "pleased", "content", "satisfied",
+        "blissful", "euphoric", "overjoyed", "jubilant", "radiant",
+        "maja", "maja aaya", "bindaas", "dhamaal", "moj", "masti",
+    },
+    "sadness": {
+        "dukh", "rona", "bura", "miss", "akela", "dard", "toot",
+        "sad", "unhappy", "miserable", "depressed", "gloomy", "melancholy",
+        "sorrowful", "heartbroken", "devastated", "grief", "mourning",
+        "lonely", "isolated", "abandoned", "rejected", "hurt", "pain",
+        "cry", "tears", "weep", "sob", "lament", "grieve",
+        "roya", "rote", "aansu", "tadap", "bichar",
+    },
+    "surprise": {
+        "kya", "seriously", "matlab", "no way", "sach", "sachchi",
+        "surprised", "shocked", "astonished", "amazed", "stunned",
+        "bewildered", "dumbfounded", "flabbergasted", "astounded",
+        "unexpected", "unbelievable", "incredible", "wow", "omg",
+        "arre", "arrey", "oye", "yaar sach", "are bhai",
+    },
+    "fear": {
+        "dar", "darr", "tension", "problem", "mushkil", "dara",
+        "afraid", "scared", "frightened", "terrified", "horrified",
+        "anxious", "nervous", "worried", "stressed", "panicked",
+        "dread", "terror", "phobia", "paranoid", "threatened",
+        "darr gaya", "darta hun", "daro mat",
+    },
+    "disgust": {
+        "yuck", "chhi", "ganda", "ulti", "bura laga", "nafrat",
+        "disgusting", "revolting", "repulsive", "nasty", "vile",
+        "gross", "horrible", "awful", "terrible", "dreadful",
+        "loathsome", "abhorrent", "detestable", "despicable",
+        "hate", "hatred", "abhor", "detest", "despise", "loathe",
+    },
+}
+
+SARCASM_PATTERNS = [
+    r"bahut\s+acch[ao]\s+hai\s*na",
+    r"haan\s+bilkul",
+    r"wah\s+kya\s+baat",
+    r"!{2,}",
+    r"(?:oh\s+)?sure\s+yaar",
+    r"bilkul\s+sahi\s+(?:hai|tha|thi)",
+    r"kitna\s+(?:accha|mast|badiya)\s+(?:hai|tha|thi)\s*(?:na|yaar)?",
+    r"great\s+yaar",
+    r"very\s+nice\s+(?:yaar|bhai)",
+]
+
+HINGLISH_WORDS = {
+    "yaar", "bhai", "mein", "hai", "toh", "kya", "nahi", "haan",
+    "abhi", "kal", "aaj", "phir", "kab", "kahan", "kyun", "kaisa",
+    "accha", "achha", "theek", "sahi", "matlab", "samjha", "dekho",
+    "suno", "bolo", "jao", "aao", "ruko", "chalo", "batao",
+    "mast", "badiya", "zabardast", "bindaas", "dhamaka", "kamaal",
+    "bilkul", "ekdum", "bahut", "bohot", "itna", "zyada",
+    "ghar", "dost", "paisa", "kaam", "time", "baat", "cheez",
+    "log", "aadmi", "ladka", "ladki", "bachha", "mama", "papa",
+    "khana", "pani", "chai", "coffee", "movie", "gana", "game",
+    "phone", "laptop", "net", "wifi", "app", "online",
+    "arre", "arrey", "oye", "yaar", "bhai", "boss", "dude",
+}
+
+TRANSLITERATION_MAP = {
+    "mera": "मेरा", "tera": "तेरा", "uska": "उसका", "hamara": "हमारा",
+    "naam": "नाम", "ghar": "घर", "dost": "दोस्त", "pyaar": "प्यार",
+    "khushi": "खुशी", "dukh": "दुःख", "zindagi": "ज़िंदगी",
+    "yaar": "यार", "bhai": "भाई", "kya": "क्या", "hai": "है",
+    "nahi": "नहीं", "haan": "हाँ", "accha": "अच्छा", "achha": "अच्छा",
+    "bahut": "बहुत", "bohot": "बहुत", "mast": "मस्त",
+    "badiya": "बढ़िया", "zabardast": "ज़बरदस्त", "kamaal": "कमाल",
+    "theek": "ठीक", "sahi": "सही", "galat": "गलत",
+    "khana": "खाना", "pani": "पानी", "chai": "चाय",
+    "aaj": "आज", "kal": "कल", "abhi": "अभी",
+    "main": "मैं", "mein": "में", "toh": "तो",
+    "kaam": "काम", "paisa": "पैसा", "time": "टाइम",
+    "phone": "फ़ोन", "movie": "मूवी", "gana": "गाना",
+    "dil": "दिल", "aankhein": "आँखें", "haath": "हाथ",
+    "gussa": "गुस्सा", "dar": "डर", "khauf": "ख़ौफ़",
+    "hasna": "हँसना", "rona": "रोना", "bolna": "बोलना",
+    "sunna": "सुनना", "dekhna": "देखना", "jaana": "जाना",
+    "aana": "आना", "karna": "करना", "rehna": "रहना",
+}
+
+
+#  DATACLASS
+@dataclass
+class HinglishAnalysis:
+    mood: str
+    intensity: float
+    confidence: float
+    emoji: str
+    sentiment: str
+    key_phrases: List[str]
+    sarcasm: bool
+    sarcasm_confidence: float
+    language_mix: Dict[str, float]
+    category: str
+    summary: str
+    emotions: Dict[str, float]
+    word_count: int
+    positive_words_found: List[str]
+    negative_words_found: List[str]
+    transliteration: Optional[str] = None
+
+
+#  MAIN ANALYZER
+class HinglishAnalyzer:
+
+    # ── Language Detection ──────────────────
+    def detect_language_mix(self, text: str) -> Dict[str, float]:
+        words = re.findall(r'\w+', text.lower())
+        if not words:
+            return {"hinglish": 0.5, "english": 0.5, "unknown": 0.0}
+
+        hinglish_count = sum(1 for w in words if w in HINGLISH_WORDS)
+        # simple English heuristic: words NOT in hinglish set, length > 2
+        english_count = sum(
+            1 for w in words
+            if w not in HINGLISH_WORDS and len(w) > 2 and w.isalpha()
+        )
+        total = len(words)
+        unknown = max(0, total - hinglish_count - english_count)
+
+        return {
+            "hinglish": round(hinglish_count / total, 2),
+            "english": round(english_count / total, 2),
+            "unknown": round(unknown / total, 2),
+        }
+
+    # ── Sarcasm Detection ───────────────────
+    def detect_sarcasm(self, text: str) -> Dict[str, Any]:
+        text_lower = text.lower()
+        matched = [p for p in SARCASM_PATTERNS if re.search(p, text_lower)]
+
+        # Contradiction: positive word + negative context
+        words = set(re.findall(r'\w+', text_lower))
+        has_positive = bool(words & POSITIVE_WORDS)
+        has_negative = bool(words & NEGATIVE_WORDS)
+        contradiction = has_positive and has_negative
+
+        score = len(matched) * 0.3 + (0.2 if contradiction else 0)
+        score = min(1.0, score)
+        return {"is_sarcastic": score > 0.3, "confidence": round(score, 2)}
+
+    # ── Emotion Detection ───────────────────
+    def detect_emotions(self, words: List[str]) -> Dict[str, float]:
+        word_set = set(words)
+        scores = {}
+        for emotion, lexicon in EMOTION_LEXICON.items():
+            matches = len(word_set & lexicon)
+            if matches:
+                scores[emotion] = round(min(1.0, matches * 0.35), 2)
+        return scores if scores else {"neutral": 1.0}
+
+    # ── Confidence ──────────────────────────
+    def calculate_confidence(self, pos: int, neg: int, total: int) -> float:
+        signal = (pos + neg) / max(total, 1)
+        if signal > 0.3:
+            return 0.92
+        elif signal > 0.15:
+            return 0.75
+        elif signal > 0.05:
+            return 0.60
+        return 0.45
+
+    # ── Transliteration ─────────────────────
+    def transliterate(self, text: str) -> str:
+        words = text.split()
+        result = []
+        for word in words:
+            clean = re.sub(r'[^\w]', '', word.lower())
+            result.append(TRANSLITERATION_MAP.get(clean, word))
+        return " ".join(result)
+
+    # ── Key Phrases ─────────────────────────
+    def extract_key_phrases(self, text: str) -> List[str]:
+        sentences = re.split(r'[.!?,]', text)
+        phrases = []
+        for s in sentences:
+            s = s.strip()
+            if len(s) > 3:
+                phrases.append(s[:80])
+        return phrases[:4]
+
+    # ── Summary ─────────────────────────────
+    def generate_summary(self, text: str, mood: str, emotions: Dict) -> str:
+        top_emotion = max(emotions, key=emotions.get) if emotions else "neutral"
+        length = "short" if len(text.split()) < 6 else "detailed"
+        return (
+            f"A {length} Hinglish message expressing {mood} sentiment "
+            f"with primary emotion: {top_emotion}."
+        )
+
+    # ── Main Analyze ────────────────────────
+    def analyze(self, text: str) -> HinglishAnalysis:
+        if not text or not text.strip():
+            return self._neutral_result()
+
+        text_lower = text.lower()
+        words = re.findall(r'\w+', text_lower)
+
+        pos_found = [w for w in words if w in POSITIVE_WORDS]
+        neg_found = [w for w in words if w in NEGATIVE_WORDS]
+        intens_count = sum(1 for w in words if w in INTENSIFIERS)
+
+        pos_count = len(pos_found)
+        neg_count = len(neg_found)
+
+        # Intensity
+        intensity = min(
+            1.0,
+            (pos_count + neg_count) * 0.20
+            + intens_count * 0.15
+            + len(words) * 0.01
+        )
+        intensity = round(intensity, 2)
+
+        # Mood & category
+        if pos_count > neg_count + 1:
+            mood, emoji, category = "positive", "😊", "praise"
+        elif neg_count > pos_count + 1:
+            mood, emoji, category = "negative", "😠", "complaint"
+        elif pos_count > 0 and neg_count > 0:
+            mood, emoji, category = "mixed", "🤨", "mixed"
+        else:
+            mood, emoji, category = "neutral", "😐", "casual"
+
+        sarcasm_result = self.detect_sarcasm(text)
+        emotions = self.detect_emotions(words)
+        lang_mix = self.detect_language_mix(text)
+        confidence = self.calculate_confidence(pos_count, neg_count, len(words))
+        key_phrases = self.extract_key_phrases(text)
+        summary = self.generate_summary(text, mood, emotions)
+        transliteration = self.transliterate(text)
+
+        return HinglishAnalysis(
+            mood=mood,
+            intensity=intensity,
+            confidence=confidence,
+            emoji=emoji,
+            sentiment=mood,
+            key_phrases=key_phrases,
+            sarcasm=sarcasm_result["is_sarcastic"],
+            sarcasm_confidence=sarcasm_result["confidence"],
+            language_mix=lang_mix,
+            category=category,
+            summary=summary,
+            emotions=emotions,
+            word_count=len(words),
+            positive_words_found=list(set(pos_found)),
+            negative_words_found=list(set(neg_found)),
+            transliteration=transliteration,
+        )
+
+    def _neutral_result(self) -> HinglishAnalysis:
+        return HinglishAnalysis(
+            mood="neutral", intensity=0.0, confidence=0.5, emoji="😐",
+            sentiment="neutral", key_phrases=[], sarcasm=False,
+            sarcasm_confidence=0.0,
+            language_mix={"hinglish": 0.5, "english": 0.5, "unknown": 0.0},
+            category="casual", summary="Empty or neutral text.",
+            emotions={"neutral": 1.0}, word_count=0,
+            positive_words_found=[], negative_words_found=[],
+            transliteration="",
+        )
+
+
+#  PUBLIC API
+_analyzer = HinglishAnalyzer()
+
+
+def analyze(text: str) -> Dict[str, Any]:
+    """Analyze a single Hinglish text."""
+    return _analyzer.analyze(text).__dict__
+
+
+def analyze_batch(texts: List[str]) -> List[Dict[str, Any]]:
+    """Analyze multiple Hinglish texts at once."""
+    return [analyze(t) for t in texts]
+
+
+def transliterate(text: str) -> str:
+    """Convert Roman Hinglish to Devanagari script."""
+    return _analyzer.transliterate(text)
+
+
+def detect_language(text: str) -> Dict[str, float]:
+    """Detect language mix in text."""
+    return _analyzer.detect_language_mix(text)
+
+
+def detect_emotion(text: str) -> Dict[str, float]:
+    """Detect emotions in text."""
+    words = re.findall(r'\w+', text.lower())
+    return _analyzer.detect_emotions(words)
+
+
+def is_sarcastic(text: str) -> Dict[str, Any]:
+    """Check if text is sarcastic."""
+    return _analyzer.detect_sarcasm(text)

hinglish_nlp-0.2.0/hinglish_nlp.egg-info/PKG-INFO

@@ -0,0 +1,178 @@
+Metadata-Version: 2.4
+Name: hinglish-nlp
+Version: 0.2.0
+Summary: Hinglish (Roman Hindi + English) NLP toolkit - Sentiment, Emotion, Sarcasm & more
+Author-email: Lalit <official.lalitpal08@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/Lalit2206/hinglish-nlp
+Project-URL: Repository, https://github.com/Lalit2206/hinglish-nlp
+Keywords: hinglish,nlp,sentiment,hindi,roman-hindi,text-analysis
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Natural Language :: Hindi
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic>=2.0
+
+# hinglish-nlp 🇮🇳
+
+A powerful NLP toolkit for **Hinglish** (Roman Hindi + English) text analysis.
+
+[![PyPI version](https://badge.fury.io/py/hinglish-nlp.svg)](https://badge.fury.io/py/hinglish-nlp)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+---
+
+## Installation
+
+```bash
+pip install hinglish-nlp
+```
+
+---
+
+## Features
+
+| Feature | Description |
+|--------|-------------|
+| ✅ Sentiment Analysis | Positive / Negative / Neutral / Mixed |
+| ✅ Emotion Detection | Joy, Anger, Sadness, Fear, Surprise, Disgust |
+| ✅ Sarcasm Detection | Pattern + contradiction based |
+| ✅ Language Mix Detection | Hinglish vs English ratio |
+| ✅ Transliteration | Roman Hindi → Devanagari |
+| ✅ Batch Processing | Multiple texts at once |
+| ✅ Key Phrase Extraction | Important phrases from text |
+| ✅ Intensity Score | 0.0 to 1.0 scale |
+| ✅ Confidence Score | How sure the model is |
+
+---
+
+## Usage
+
+### Basic Sentiment Analysis
+```python
+from hinglish import analyze
+
+result = analyze("yaar bahut mast movie thi!")
+print(result["mood"])        # positive
+print(result["emoji"])       # 😊
+print(result["intensity"])   # 0.45
+print(result["confidence"])  # 0.75
+```
+
+### Emotion Detection
+```python
+from hinglish import detect_emotion
+
+emotions = detect_emotion("mujhe bahut gussa aa raha hai!")
+print(emotions)  # {'anger': 0.35}
+
+emotions = detect_emotion("aaj bahut khushi hui yaar!")
+print(emotions)  # {'joy': 0.7}
+```
+
+### Sarcasm Detection
+```python
+from hinglish import is_sarcastic
+
+result = is_sarcastic("haan bilkul, bahut accha hai na!!")
+print(result)
+# {'is_sarcastic': True, 'confidence': 0.6}
+```
+
+### Language Mix Detection
+```python
+from hinglish import detect_language
+
+mix = detect_language("yaar ye movie bahut boring thi")
+print(mix)
+# {'hinglish': 0.5, 'english': 0.33, 'unknown': 0.17}
+```
+
+### Transliteration (Roman → Devanagari)
+```python
+from hinglish import transliterate
+
+text = transliterate("mera naam lalit hai")
+print(text)  # मेरा नाम ललित है
+```
+
+### Batch Processing
+```python
+from hinglish import analyze_batch
+
+texts = [
+    "yaar mast movie thi!",
+    "bilkul bakwaas tha yaar",
+    "theek thak tha, kuch khaas nahi"
+]
+
+results = analyze_batch(texts)
+for r in results:
+    print(r["mood"], r["emoji"])
+# positive 😊
+# negative 😠
+# neutral  😐
+```
+
+### Full Analysis
+```python
+from hinglish import analyze
+
+result = analyze("Phone ki battery toh bekar hai but camera mast hai")
+print(result)
+# {
+#   'mood': 'mixed',
+#   'intensity': 0.3,
+#   'confidence': 0.75,
+#   'emoji': '🤨',
+#   'sentiment': 'mixed',
+#   'key_phrases': ['Phone ki battery toh bekar hai but camera mast hai'],
+#   'sarcasm': False,
+#   'sarcasm_confidence': 0.0,
+#   'language_mix': {'hinglish': 0.36, 'english': 0.55, 'unknown': 0.09},
+#   'category': 'mixed',
+#   'summary': 'A detailed Hinglish message expressing mixed sentiment...',
+#   'emotions': {'disgust': 0.35},
+#   'word_count': 11,
+#   'positive_words_found': ['mast'],
+#   'negative_words_found': ['bekar'],
+#   'transliteration': 'Phone की battery तो bekar है but camera मस्त है'
+# }
+```
+
+---
+
+## Output Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `mood` | str | positive / negative / neutral / mixed |
+| `intensity` | float | 0.0 – 1.0 |
+| `confidence` | float | 0.0 – 1.0 |
+| `emoji` | str | Visual mood indicator |
+| `sentiment` | str | Same as mood |
+| `key_phrases` | list | Important phrases |
+| `sarcasm` | bool | Is text sarcastic? |
+| `sarcasm_confidence` | float | Sarcasm confidence score |
+| `language_mix` | dict | hinglish / english / unknown ratio |
+| `category` | str | praise / complaint / casual / mixed |
+| `summary` | str | Short summary of the text |
+| `emotions` | dict | Detected emotions with scores |
+| `word_count` | int | Total word count |
+| `positive_words_found` | list | Positive words detected |
+| `negative_words_found` | list | Negative words detected |
+| `transliteration` | str | Roman → Devanagari |
+
+---
+
+## Author
+
+**Lalit** — [lalitpal2206](https://pypi.org/user/lalitpal2206/)
+
+## License
+
+MIT License

hinglish_nlp-0.2.0/hinglish_nlp.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+pyproject.toml
+hinglish/__init__.py
+hinglish/analyzer.py
+hinglish_nlp.egg-info/PKG-INFO
+hinglish_nlp.egg-info/SOURCES.txt
+hinglish_nlp.egg-info/dependency_links.txt
+hinglish_nlp.egg-info/requires.txt
+hinglish_nlp.egg-info/top_level.txt

hinglish_nlp-0.2.0/hinglish_nlp.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

hinglish_nlp-0.2.0/hinglish_nlp.egg-info/requires.txt

@@ -0,0 +1 @@
+pydantic>=2.0

hinglish_nlp-0.2.0/hinglish_nlp.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+dist
+hinglish

hinglish_nlp-0.2.0/pyproject.toml

@@ -0,0 +1,28 @@
+[project]
+name = "hinglish-nlp"
+version = "0.2.0"
+description = "Hinglish (Roman Hindi + English) NLP toolkit - Sentiment, Emotion, Sarcasm & more"
+readme = "README.md"
+requires-python = ">=3.9"
+license = {text = "MIT"}
+authors = [
+    {name = "Lalit", email = "official.lalitpal08@gmail.com"}]
+keywords = ["hinglish", "nlp", "sentiment", "hindi", "roman-hindi", "text-analysis"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Text Processing :: Linguistic",
+    "Natural Language :: Hindi",
+]
+
+dependencies = [
+    "pydantic>=2.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/Lalit2206/hinglish-nlp"
+Repository = "https://github.com/Lalit2206/hinglish-nlp"
+
+[tool.setuptools.packages.find]
+where = ["."]

hinglish_nlp-0.2.0/setup.cfg

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