Duplicate from TangibleAI/mathtext-nlu

Co-authored-by: Hobson Lane <Hobson@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,100 @@
+# Temporary and binary files
+venv
+*.bak
+*~
+*.py[cod]
+*.so
+*.cfg
+!.isort.cfg
+*.orig
+*.log
+*.pot
+.pytest_cache/*
+__pycache__/*
+.DS_*
+.cache/*
+.*.swp
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+.coverage*
+cache_dir/
+
+
+# pypi package setup files
+# pyproject must not be in root dir for `pip install -e .` to work
+# pyproject.toml
+!scripts/pyproject.toml
+!setup.cfg
+
+# Internal working cache for poetry
+poetry.lock
+
+
+# Project files
+.ropeproject
+.project
+.pydevproject
+.settings
+.idea
+.vscode
+tags
+*.code-workspace
+*.sublime-workspace
+
+# Package files
+*.egg
+*.eggs/
+.installed.cfg
+*.egg-info
+
+# Unittest and coverage
+htmlcov/*
+.coverage
+.tox
+junit.xml
+coverage.xml
+.pytest_cache/
+pytest-results*
+
+# Build and docs folder/files
+build/*
+dist/*
+sdist/*
+docs/api/*
+docs/_rst/*
+docs/_build/*
+cover/*
+runs/*
+MANIFEST
+
+# Mac
+__MACOSX
+
+# KDE
+.directory
+
+# BigData and Models
+db.sqlite3
+*.bz2
+*.zip
+*.pkl
+*.npy
+**/data/qa-models/*
+**/data/models/pulse/*
+**/data/predictions*
+**/data/squad/*
+**/data/testsets/accuracy_report*
+**/albert-large*
+**/data/corpora/wikipedia/wikipedia-titles*
+
+# Per-project virtualenvs
+.venv*/
+
+# docs html
+docs/**/*.html
+
+# secrets
+.env
+.bash_env
+**/*secret*
+**/*private*

README.md

@@ -0,0 +1,13 @@
+---
+title: MathText
+app_file: app.py
+sdk: gradio
+sdk_version: 3.0.2
+license: agpl-3.0
+duplicated_from: TangibleAI/mathtext-nlu
+---
+
+## MathText NLU
+
+Natural Language Understanding for math symbols, digits, and words with a Gradio user interface and REST API.
+

app.py

@@ -0,0 +1,179 @@
+import inspect
+import json
+import logging
+import os
+import gradio as gr
+from gradio import routes
+import spacy  # noqa
+from typing import List, Type
+
+TOKENS2INT_ERROR_INT = 32202
+
+log = logging.getLogger()
+
+ONES = [
+    "zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
+    "nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
+    "sixteen", "seventeen", "eighteen", "nineteen",
+]
+
+# token_mapping = json.load(open('str_mapping.json'))
+CHAR_MAPPING = {
+    "-": " ",
+    "_": " ",
+}
+CHAR_MAPPING.update((str(i), word) for i, word in enumerate([" " + s + " " for s in ONES]))
+
+TOKEN_MAPPING = dict(enumerate([" " + s + " " for s in ONES]))
+
+BQ_JSON = os.environ['BQ_JSON']
+
+
+def tokenize(text):
+    return text.split()
+
+
+def detokenize(tokens):
+    return ' '.join(tokens)
+
+
+def replace_tokens(tokens, token_mapping=TOKEN_MAPPING):
+    return [token_mapping.get(tok, tok) for tok in tokens]
+
+
+def replace_chars(text, char_mapping=CHAR_MAPPING):
+    return ''.join((char_mapping.get(c, c) for c in text))
+
+
+def tokens2int(tokens, numwords={}):
+    """ Convert an English str containing number words into an int
+
+    >>> text2int("nine")
+    9
+    >>> text2int("forty two")
+    42
+    >>> text2int("1 2 three")
+    123
+    """
+    if not numwords:
+
+        tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"]
+
+        scales = ["hundred", "thousand", "million", "billion", "trillion"]
+
+        numwords["and"] = (1, 0)
+        for idx, word in enumerate(ONES):
+            numwords[word] = (1, idx)
+        for idx, word in enumerate(tens):
+            numwords[word] = (1, idx * 10)
+        for idx, word in enumerate(scales):
+            numwords[word] = (10 ** (idx * 3 or 2), 0)
+
+    current = result = 0
+
+    for word in tokens:
+        if word not in numwords:
+            raise Exception("Illegal word: " + word)
+
+        scale, increment = numwords[word]
+        current = current * scale + increment
+        if scale > 100:
+            result += current
+            current = 0
+
+    return str(result + current)
+
+
+def text2int(text):
+    return tokens2int(tokenize(replace_chars(text)))
+
+
+def try_text2int(text):
+    text = str(text)
+    try:
+        intstr = tokens2int(tokens2int(tokenize(replace_chars(text))))
+    except Exception as e:
+        log.error(str(e))
+        log.error(f'User input: {text}')
+        intstr = TOKENS2INT_ERROR_INT
+    return str(intstr)
+
+
+def try_text2int_preprocessed(text):
+    text = str(text)
+    try:
+        tokens = replace_tokens(tokenize(replace_chars(str(text))))
+    except Exception as e:
+        log.error(str(e))
+        tokens = text.split()
+    try:
+        intstr = tokens2int(tokens)
+    except Exception as e:
+        log.error(str(e))
+        intstr = str(TOKENS2INT_ERROR_INT)
+    return intstr
+
+
+def get_types(cls_set: List[Type], component: str):
+    docset = []
+    types = []
+    if component == "input":
+        for cls in cls_set:
+            doc = inspect.getdoc(cls)
+            doc_lines = doc.split("\n")
+            docset.append(doc_lines[1].split(":")[-1])
+            types.append(doc_lines[1].split(")")[0].split("(")[-1])
+    else:
+        for cls in cls_set:
+            doc = inspect.getdoc(cls)
+            doc_lines = doc.split("\n")
+            docset.append(doc_lines[-1].split(":")[-1])
+            types.append(doc_lines[-1].split(")")[0].split("(")[-1])
+    return docset, types
+
+
+routes.get_types = get_types
+
+with gr.Blocks() as html_block:
+    gr.Markdown("# Gradio Blocks (3.0) with REST API")
+    textbox_input = gr.Textbox(
+        value="forty-two",
+        label="Input number words:",
+    )
+    button_text2int = gr.Button("text2int")
+    button_text2int_preprocessed = gr.Button("text2int with preprocessing")
+    textbox_output = gr.Textbox(
+        value="42",
+        label="Output integer:"
+    )
+    button_text2int.click(try_text2int, inputs=[textbox_input], outputs=[textbox_output])
+    button_text2int_preprocessed.click(try_text2int_preprocessed, inputs=[textbox_input], outputs=[textbox_output])
+    gr.Markdown(r"""
+
+## API
+
+You can select which function to run using the `fn_index` argument:
+
+```python
+import requests
+
+requests.post(
+    url="https://Hobson-gradio-rest-api.hf.space/api/predict/", json={"data": ["one hundred forty-two"], "fn_index": 0}
+).json()
+```
+
+Or using `curl`:
+
+```bash
+curl -X POST https://Hobson-gradio-rest-api.hf.space/api/predict/ -H 'Content-Type: application/json' -d '{"data": ["one hundred forty-two"], "fn_index": 0}'
+```
+""" + f"{json.loads(BQ_JSON)['type']}")
+
+interface = gr.Interface(lambda: None, inputs=[textbox_input], outputs=[textbox_output])
+
+html_block.input_components = interface.input_components
+html_block.output_components = interface.output_components
+html_block.examples = None
+html_block.predict_durations = []
+
+bapp = html_block.launch()

requirements.txt

@@ -0,0 +1,4 @@
+spacy
+pandas
+pandas-gbq
+gradio>=3.0.2,<3.1.0