with-english-name-spacy.py

import re
from fastapi import FastAPI
from pydantic import BaseModel
from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForTokenClassification
import dateparser
from datetime import datetime
import spacy

app = FastAPI()

# Load classification and summarization models
classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
summarizer_tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-small")
summarizer_model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-small")

# Load spaCy English model for name/entity detection
try:
    nlp = spacy.load("en_core_web_sm")
except:
    import subprocess
    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
    nlp = spacy.load("en_core_web_sm")

# Labels for classification
labels = [
  "task", "event", "reminder", "meeting", "relationship", "note", "journal", "memory", "status_update",
  "sick_notice", "out_of_office", "travel_plan", "celebration", "emotion", "other"
]

class TextInput(BaseModel):
    text: str

def extract_dates(text):
    time_expressions = re.findall(
        r'\b(kal|aaj|parso|raat|subah|shaam|dopahar|[0-9]{1,2} baje|next week|tomorrow|today|yesterday|Monday|Tuesday|Wednesday|Thursday|Friday|Saturday|Sunday|[\d]{1,2}/[\d]{1,2}/[\d]{2,4})\b',
        text, flags=re.IGNORECASE)
    parsed = [str(dateparser.parse(t)) for t in time_expressions if dateparser.parse(t)]
    return list(set(parsed)), list(set(time_expressions))

def detect_tense(parsed_dates):
    now = datetime.now()
    tenses = set()
    for d in parsed_dates:
        dt = dateparser.parse(d)
        if not dt:
            continue
        if dt < now:
            tenses.add("past")
        elif dt > now:
            tenses.add("future")
        else:
            tenses.add("present")
    return list(tenses) if tenses else ["unknown"]

def generate_summary(text):
    input_ids = summarizer_tokenizer("summarize: " + text, return_tensors="pt").input_ids
    output_ids = summarizer_model.generate(input_ids, max_length=60, num_beams=4, early_stopping=True)
    return summarizer_tokenizer.decode(output_ids[0], skip_special_tokens=True)


def extract_people(text):
    doc = nlp(text)
    return list(set(ent.text for ent in doc.ents if ent.label_ in ["PERSON"]))

def estimate_mood(text):
    text_lower = text.lower()
    mood_map = {
        "happy": ["happy", "excited", "joy", "grateful"],
        "sad": ["sad", "upset", "crying", "lonely"],
        "angry": ["angry", "annoyed", "frustrated", "irritated"],
        "nervous": ["nervous", "anxious", "scared"],
        "unwell": ["sick", "unwell", "not feeling well", "fever", "cold", "headache"],
        "neutral": []
    }

    for mood, keywords in mood_map.items():
        for kw in keywords:
            if kw in text_lower:
                return mood
    return "neutral"

def generate_tags(label, text):
    base_tags = [label]
    keywords = re.findall(r'\b[a-zA-Z]{4,}\b', text.lower())
    force_tags = []

    if any(w in text.lower() for w in ["sick", "unwell", "not feeling well", "fever"]):
        force_tags += ["sick", "leave"]
    if "work" in text.lower():
        force_tags.append("work")

    return list(set(base_tags + force_tags + keywords))


@app.post("/analyze")
async def analyze(input: TextInput):
    text = input.text

    classification = classifier(text, labels)
    best_label = classification['labels'][0]
    scores = dict(zip(classification['labels'], classification['scores']))

    parsed_dates, time_mentions = extract_dates(text)
    tenses = detect_tense(parsed_dates)
    summary = generate_summary(text)
    people = extract_people(text)
    mood = estimate_mood(text)
    tags = generate_tags(best_label, text)

    return {
        "type": best_label,
        "confidence_scores": scores,
        "time_mentions": time_mentions,
        "parsed_dates": parsed_dates,
        "tense": tenses,
        "summary": summary,
        "people": people,
        "mood": mood,
        "tags": tags
    }