Added gray-scale and negative preprocessing for input images

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,162 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-.DS_Store

README.md

@@ -1,12 +1,12 @@
 ---
-title: Deprem OCR
+title: Deprem Ocr 2
 emoji: 👀
 colorFrom: green
 colorTo: blue
 sdk: gradio
 sdk_version: 3.17.0
 app_file: app.py
-pinned: true
+pinned: false
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,152 +1,157 @@
-from PIL import ImageFilter, Image
-from easyocr import Reader
 import gradio as gr
-import numpy as np
+from easyocr import Reader
+from PIL import Image
+import io
+import json
+import csv
 import openai
 import ast
-from transformers import pipeline
 import os
+from deta import Deta
+import cv2
 
-from openai_api import OpenAI_API
-import utils
 
-openai.api_key = os.getenv("API_KEY")
+openai.api_key = os.getenv('API_KEY')
 reader = Reader(["tr"])
 
 
-def get_text(input_img):
-    img = Image.fromarray(input_img)
-    detailed = np.asarray(img.filter(ImageFilter.DETAIL))
-    result = reader.readtext(detailed, detail=0, paragraph=True)
-    return " ".join(result)
-
-
-# Submit button
 def get_parsed_address(input_img):
 
     address_full_text = get_text(input_img)
-    return ner_response(address_full_text)
+    return openai_response(address_full_text)
 
 
-def save_deta_db(input):
-    eval_result = ast.literal_eval(input)
-    utils.write_db(eval_result)
-    return
+def preprocess_img(inp_image):
+    gray = cv2.cvtColor(inp_image, cv2.COLOR_BGR2GRAY)
+    gray_img = cv2.bitwise_not(gray)
+    return gray_img
+
+
+def get_text(image):
+    processed_image = preprocess_img(inp_image=image)
+    result = reader.readtext(processed_image,
+                             detail=0,
+                             paragraph=True
+                             )
 
+    return " ".join(result)
+
+
+def save_csv(mahalle, il, sokak, apartman):
+    adres_full = [mahalle, il, sokak, apartman]
+
+    with open("adress_book.csv", "a", encoding="utf-8") as f:
+        write = csv.writer(f)
+        write.writerow(adres_full)
+    return adres_full
 
-def update_component():
-    return gr.update(value="Gönderildi, teşekkürler.", visible=True)
 
+def get_json(mahalle, il, sokak, apartman):
+    adres = {"mahalle": mahalle, "il": il, "sokak": sokak, "apartman": apartman}
+    dump = json.dumps(adres, indent=4, ensure_ascii=False)
+    return dump
 
-def clear_textbox(value):
-    return gr.update(value="")
+def write_db(data_dict):
+    # 2) initialize with a project key
+    deta_key = os.getenv('DETA_KEY')
+    deta = Deta(deta_key)
+
+    # 3) create and use as many DBs as you want!
+    users = deta.Base("deprem-ocr")
+    users.insert(data_dict)
 
 
 def text_dict(input):
     eval_result = ast.literal_eval(input)
+    write_db(eval_result)
+
     return (
-        str(eval_result["il"]),
-        str(eval_result["ilce"]),
-        str(eval_result["mahalle"]),
-        str(eval_result["sokak"]),
-        str(eval_result["Apartman/site"]),
-        str(eval_result["no"]),
-        str(eval_result["ad-soyad"]),
-        str(eval_result["dis kapi no"]),
+        str(eval_result['city']),
+        str(eval_result['distinct']),
+        str(eval_result['neighbourhood']),
+        str(eval_result['street']),
+        str(eval_result['address']),
+        str(eval_result['tel']),
+        str(eval_result['name_surname']),
+        str(eval_result['no']),
     )
+        
+def openai_response(ocr_input):
+    prompt = f"""Tabular Data Extraction You are a highly intelligent and accurate tabular data extractor from 
+            plain text input and especially from emergency text that carries address information, your inputs can be text 
+            of arbitrary size, but the output should be in [{{'tabular': {{'entity_type': 'entity'}} }}] JSON format Force it 
+            to only extract keys that are shared as an example in the examples section, if a key value is not found in the 
+            text input, then it should be ignored. Have only city, distinct, neighbourhood, 
+            street, no, tel, name_surname, address Examples: Input: Deprem sırasında evimizde yer alan adresimiz: İstanbul, 
+            Beşiktaş, Yıldız Mahallesi, Cumhuriyet Caddesi No: 35, cep telefonu numaram 5551231256, adim Ahmet Yilmaz 
+            Output: {{'city': 'İstanbul', 'distinct': 'Beşiktaş', 'neighbourhood': 'Yıldız Mahallesi', 'street': 'Cumhuriyet Caddesi', 'no': '35', 'tel': '5551231256', 'name_surname': 'Ahmet Yılmaz', 'address': 'İstanbul, Beşiktaş, Yıldız Mahallesi, Cumhuriyet Caddesi No: 35'}}
+            Input: {ocr_input}
+            Output:
+        """
 
-
-def ner_response(ocr_input):
-
-    ner_pipe = pipeline("token-classification","deprem-ml/deprem-ner", aggregation_strategy="first")
-    predictions = ner_pipe(ocr_input)
-    resp = {}
-
-    for item in predictions:
-        print(item)
-        key = item["entity_group"]
-        resp[key] = item["word"]
-    
+    response = openai.Completion.create(
+        model="text-davinci-003",
+        prompt=prompt,
+        temperature=0,
+        max_tokens=300,
+        top_p=1,
+        frequency_penalty=0.0,
+        presence_penalty=0.0,
+        stop=["\n"],
+    )
+    resp = response["choices"][0]["text"]
+    print(resp)
+    resp = eval(resp.replace("'{", "{").replace("}'", "}"))
     resp["input"] = ocr_input
-    dict_keys = ["il", "ilce", "mahalle", "sokak", "Apartman/site", "no", "ad-soyad", "dis kapi no"]
+    dict_keys = [
+    'city',
+    'distinct',
+    'neighbourhood',
+    'street',
+    'no',
+    'tel',
+    'name_surname',
+    'address',
+    'input',
+    ]
     for key in dict_keys:
         if key not in resp.keys():
-            resp[key] = ""
+            resp[key] = ''
     return resp
 
 
-# User Interface
 with gr.Blocks() as demo:
     gr.Markdown(
-        """
-    # Enkaz Bildirme Uygulaması
     """
-    )
-    gr.Markdown(
-        "Bu uygulamada ekran görüntüsü sürükleyip bırakarak AFAD'a enkaz bildirimi yapabilirsiniz. Mesajı metin olarak da girebilirsiniz, tam adresi ayrıştırıp döndürür. API olarak kullanmak isterseniz sayfanın en altında use via api'ya tıklayın."
-    )
+    # Enkaz Bildirme Uygulaması
+    """)
+    gr.Markdown("Bu uygulamada ekran görüntüsü sürükleyip bırakarak AFAD'a enkaz bildirimi yapabilirsiniz. Mesajı metin olarak da girebilirsiniz, tam adresi ayrıştırıp döndürür. API olarak kullanmak isterseniz sayfanın en altında use via api'ya tıklayın.")
     with gr.Row():
-        with gr.Column():
-            img_area = gr.Image(label="Ekran Görüntüsü yükleyin 👇")
-            img_area_button = gr.Button(value="Görüntüyü İşle", label="Submit")
-
-        with gr.Column():
-            text_area = gr.Textbox(label="Metin yükleyin 👇 ", lines=8)
-            text_area_button = gr.Button(value="Metni Yükle", label="Submit")
-
+        img_area = gr.Image(label="Ekran Görüntüsü yükleyin 👇")
+        ocr_result = gr.Textbox(label="Metin yükleyin 👇 ")
     open_api_text = gr.Textbox(label="Tam Adres")
-
+    submit_button = gr.Button(label="Yükle")
     with gr.Column():
         with gr.Row():
-            il = gr.Textbox(label="İl", interactive=True, show_progress=False)
-            ilce = gr.Textbox(label="İlçe", interactive=True, show_progress=False)
+            city = gr.Textbox(label="İl")
+            distinct = gr.Textbox(label="İlçe")
         with gr.Row():
-            mahalle = gr.Textbox(
-                label="Mahalle", interactive=True, show_progress=False
-            )
-            sokak = gr.Textbox(
-                label="Sokak/Cadde/Bulvar", interactive=True, show_progress=False
-            )
+            neighbourhood = gr.Textbox(label="Mahalle")
+            street = gr.Textbox(label="Sokak/Cadde/Bulvar")
         with gr.Row():
-            no = gr.Textbox(label="Telefon", interactive=True, show_progress=False)
+            tel = gr.Textbox(label="Telefon")
         with gr.Row():
-            ad_soyad = gr.Textbox(
-                label="İsim Soyisim", interactive=True, show_progress=False
-            )
-            apartman = gr.Textbox(label="apartman", interactive=True, show_progress=False)
+            name_surname = gr.Textbox(label="İsim Soyisim")
+            address = gr.Textbox(label="Adres")
         with gr.Row():
-            dis_kapi_no = gr.Textbox(label="Kapı No", interactive=True, show_progress=False)
+            no = gr.Textbox(label="Kapı No")
 
-    img_area_button.click(
-        get_parsed_address,
-        inputs=img_area,
-        outputs=open_api_text,
-        api_name="upload-image",
-    )
 
-    text_area_button.click(
-        ner_response, text_area, open_api_text, api_name="upload-text"
-    )
+    submit_button.click(get_parsed_address, inputs = img_area, outputs = open_api_text, api_name="upload_image")
 
+    ocr_result.change(openai_response, ocr_result, open_api_text, api_name="upload-text")
 
-    open_api_text.change(
-        text_dict,
-        open_api_text,
-        [il, ilce, mahalle, sokak, no, apartman, ad_soyad, dis_kapi_no],
-    )
-    ocr_button = gr.Button(value="Sadece OCR kullan")
-    ocr_button.click(
-        get_text,
-        inputs=img_area,
-        outputs=text_area,
-        api_name="get-ocr-output",
-    )
-    submit_button = gr.Button(value="Veriyi Birimlere Yolla")
-    submit_button.click(save_deta_db, open_api_text)
-    done_text = gr.Textbox(label="Done", value="Not Done", visible=False)
-    submit_button.click(update_component, outputs=done_text)
-    for txt in [il, ilce, mahalle, sokak, apartman, no, ad_soyad, dis_kapi_no]:
-        submit_button.click(fn=clear_textbox, inputs=txt, outputs=txt)
+    open_api_text.change(text_dict, open_api_text, [city, distinct, neighbourhood, street, address, tel, name_surname, no])
 
 
 if __name__ == "__main__":

db_utils.py

@@ -1,41 +0,0 @@
-from deta import Deta  # Import Deta
-from pprint import pprint
-import os
-
-deta_key = os.getenv("DETA_KEY")
-deta = Deta(deta_key)
-db = deta.Base("deprem-ocr")
-
-
-def get_users_by_city(city_name, limit=10):
-
-    user = db.fetch({"city": city_name.capitalize()}, limit=limit).items
-    return user
-
-
-def get_all():
-    res = db.fetch()
-    all_items = res.items
-
-    # fetch until last is 'None'
-    while res.last:
-        res = db.fetch(last=res.last)
-        all_items += res.items
-    return all_items
-
-
-def write_db(data_dict):
-    # 2) initialize with a project key
-    deta_key = os.getenv("DETA_KEY")
-    deta = Deta(deta_key)
-
-    # 3) create and use as many DBs as you want!
-    users = deta.Base("deprem-ocr")
-    users.insert(data_dict)
-    print("Pushed to db")
-
-
-def get_latest_row(last):
-    all_items = get_all()
-    latest_items = all_items[-last:]
-    return latest_items

openai_api.py

@@ -1,31 +0,0 @@
-import openai
-import os
-
-
-class OpenAI_API:
-    def __init__(self):
-        self.openai_api_key = ""
-
-    def single_request(self, address_text):
-
-        openai.api_type = "azure"
-        openai.api_base = "https://afet-org.openai.azure.com/"
-        openai.api_version = "2022-12-01"
-        openai.api_key = os.getenv("API_KEY")
-
-        response = openai.Completion.create(
-            engine="afet-org",
-            prompt=address_text,
-            temperature=0.0,
-            max_tokens=500,
-            top_p=1,
-            # n=1,
-            # logprobs=0,
-            # echo=False,
-            stop=["\n"],
-            frequency_penalty=0,
-            presence_penalty=0,
-            # best_of=1,
-        )
-
-        return response

requirements.txt

@@ -3,4 +3,5 @@ Pillow
 easyocr
 gradio
 deta
-transformers
+opencv-python
+opencv-contrib-python

utils.py

@@ -1,53 +0,0 @@
-import cv2
-import csv
-import json
-from deta import Deta
-import os
-import requests
-
-
-def preprocess_img(inp_image):
-    gray = cv2.cvtColor(inp_image, cv2.COLOR_BGR2GRAY)
-    gray_img = cv2.bitwise_not(gray)
-    return gray_img
-
-
-def save_csv(mahalle, il, sokak, apartman):
-    adres_full = [mahalle, il, sokak, apartman]
-
-    with open("adress_book.csv", "a", encoding="utf-8") as f:
-        write = csv.writer(f)
-        write.writerow(adres_full)
-    return adres_full
-
-
-def get_json(mahalle, il, sokak, apartman):
-    adres = {"mahalle": mahalle, "il": il, "sokak": sokak, "apartman": apartman}
-    dump = json.dumps(adres, indent=4, ensure_ascii=False)
-    return dump
-
-
-def write_db(data_dict):
-    # 2) initialize with a project key
-    deta_key = os.getenv("DETA_KEY")
-    deta = Deta(deta_key)
-
-    # 3) create and use as many DBs as you want!
-    users = deta.Base("deprem-ocr")
-    users.insert(data_dict)
-
-
-def ner_response(ocr_input):
-    API_URL = "https://api-inference.huggingface.co/models/deprem-ml/deprem-ner"
-    headers = {"Authorization": "Bearer xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
-
-    def query(payload):
-        response = requests.post(API_URL, headers=headers, json=payload)
-        return response.json()
-
-    output = query(
-        {
-            "inputs": ocr_input,
-        }
-    )
-    return output