package mathtext for pip install -e .

app.py

@@ -1,108 +1,103 @@
 import gradio as gr
 import spacy  # noqa
-from transformers import pipeline
 
-from mathtext.nlutils import text2int
-
-
-sentiment = pipeline(task="sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
-
-
-def get_sentiment(text):
-    return sentiment(text)
-
-
-with gr.Blocks() as html_block:
-    gr.Markdown("# Rori - Mathbot")
-
-    with gr.Tab("Text to integer"):
-        inputs_text2int = [gr.Text(
-            placeholder="Type a number as text or a sentence",
-            label="Text to process",
-            value="forty two")]
-
-        outputs_text2int = gr.Textbox(label="Output integer")
-
-        button_text2int = gr.Button("text2int")
-
-        button_text2int.click(
-            fn=text2int,
-            inputs=inputs_text2int,
-            outputs=outputs_text2int,
-            api_name="text2int",
-        )
-
-        examples_text2int = [
-            "one thousand forty seven",
-            "one hundred",
-        ]
-
-        gr.Examples(examples=examples_text2int, inputs=inputs_text2int)
-
-        gr.Markdown(r"""
-        ## API
-        ```python
-        import requests
-
-        requests.post(
-            url="https://tangibleai-mathtext.hf.space/run/text2int", json={"data": ["one hundred forty five"]}
-        ).json()
-        ```
-
-        Or using `curl`:
-
-        ```bash
-        curl -X POST https://tangibleai-mathtext.hf.space/run/text2int -H 'Content-Type: application/json' -d '{"data": ["one hundred forty five"]}'
-        ```
-        """)
-
-    with gr.Tab("Sentiment Analysis"):
-        inputs_sentiment = [
-            gr.Text(placeholder="Type a number as text or a sentence", label="Text to process",
-                    value="I really like it!"),
-        ]
-
-        outputs_sentiment = gr.Textbox(label="Sentiment result")
-
-        button_sentiment = gr.Button("sentiment analysis")
-
-        button_sentiment.click(
-            get_sentiment,
-            inputs=inputs_sentiment,
-            outputs=outputs_sentiment,
-            api_name="sentiment-analysis"
-        )
-
-        examples_sentiment = [
-            ["Totally agree!"],
-            ["Sorry, I can not accept this!"],
-        ]
-
-        gr.Examples(examples=examples_sentiment, inputs=inputs_sentiment)
-
-        gr.Markdown(r"""
-        ## API
-        ```python
-        import requests
-        
-        requests.post(
-            url="https://tangibleai-mathtext.hf.space/run/sentiment-analysis", json={"data": ["You are right!"]}
-        ).json()
-        ```
-        
-        Or using `curl`:
-        
-        ```bash
-        curl -X POST https://tangibleai-mathtext.hf.space/run/sentiment-analysis -H 'Content-Type: application/json' -d '{"data": ["You are right!"]}'
-        ```
-        """)
+from mathtext.nlutils import text2int, get_sentiment
+
+
+def build_html_block():
+    with gr.Blocks() as html_block:
+        gr.Markdown("# Rori - Mathbot")
+
+        with gr.Tab("Text to integer"):
+            inputs_text2int = [gr.Text(
+                placeholder="Type a number as text or a sentence",
+                label="Text to process",
+                value="forty two")]
+
+            outputs_text2int = gr.Textbox(label="Output integer")
+
+            button_text2int = gr.Button("text2int")
+
+            button_text2int.click(
+                fn=text2int,
+                inputs=inputs_text2int,
+                outputs=outputs_text2int,
+                api_name="text2int",
+            )
+
+            examples_text2int = [
+                "one thousand forty seven",
+                "one hundred",
+            ]
+
+            gr.Examples(examples=examples_text2int, inputs=inputs_text2int)
+
+            gr.Markdown(r"""
+            ## API
+            ```python
+            import requests
+
+            requests.post(
+                url="https://tangibleai-mathtext.hf.space/run/text2int", json={"data": ["one hundred forty five"]}
+            ).json()
+            ```
+
+            Or using `curl`:
+
+            ```bash
+            curl -X POST https://tangibleai-mathtext.hf.space/run/text2int -H 'Content-Type: application/json' -d '{"data": ["one hundred forty five"]}'
+            ```
+            """)
+
+        with gr.Tab("Sentiment Analysis"):
+            inputs_sentiment = [
+                gr.Text(placeholder="Type a number as text or a sentence", label="Text to process",
+                        value="I really like it!"),
+            ]
+
+            outputs_sentiment = gr.Textbox(label="Sentiment result")
+
+            button_sentiment = gr.Button("sentiment analysis")
+
+            button_sentiment.click(
+                get_sentiment,
+                inputs=inputs_sentiment,
+                outputs=outputs_sentiment,
+                api_name="sentiment-analysis"
+            )
+
+            examples_sentiment = [
+                ["Totally agree!"],
+                ["Sorry, I can not accept this!"],
+            ]
+
+            gr.Examples(examples=examples_sentiment, inputs=inputs_sentiment)
+
+            gr.Markdown(r"""
+            ## API
+            ```python
+            import requests
+            
+            requests.post(
+                url="https://tangibleai-mathtext.hf.space/run/sentiment-analysis", json={"data": ["You are right!"]}
+            ).json()
+            ```
+            
+            Or using `curl`:
+            
+            ```bash
+            curl -X POST https://tangibleai-mathtext.hf.space/run/sentiment-analysis -H 'Content-Type: application/json' -d '{"data": ["You are right!"]}'
+            ```
+            """)
+    return html_block
 
 # interface = gr.Interface(lambda x: x, inputs=["text"], outputs=["text"])
 # html_block.input_components = interface.input_components
 # html_block.output_components = interface.output_components
 # html_block.examples = None
+# html_block.predict_durations = []
 
-html_block.predict_durations = []
 
 if __name__ == "__main__":
+    html_block = build_html_block()
     html_block.launch()

nlutils.py → mathtext/nlutils.py

@@ -1,6 +1,7 @@
 import spacy  # noqa
 import time
 from editdistance import eval as edit_dist
+from transformers import pipeline
 
 # import os
 # os.environ['KMP_DUPLICATE_LIB_OK']='True'
@@ -318,6 +319,13 @@ def correct_number_text(text):
     # TODO
 
 
+sentiment = pipeline(task="sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+
+
+def get_sentiment(text):
+    return sentiment(text)
+
+
 def robust_text2int(text):
     """ Correct spelling of number words in text before using text2int """
     try:

pyproject.toml

@@ -1,28 +1,15 @@
-[build-system]
-requires = ["setuptools>=40.8.0", "wheel"]
-build-backend = "setuptools.build_meta:__legacy__"
-
-[project]
+[tool.poetry]
 name = "MathText"
-packages = {find = "mathtext"}
 version = "0.0.3"
 authors = [
-  {name="Sebastian Larsen", email="sebastianlarson22@gmail.com"},
-  {name="Çetin ÇAKIR", email="cetincakirtr@gmail.com"},
-  {name="Hobson Lane", email="gitlab@totalgood.com"},
+  "Sebastian Larsen <sebastianlarson22@gmail.com>",
+  "Çetin ÇAKIR <cetincakirtr@gmail.com>",
+  "Hobson Lane <gitlab@totalgood.com>",
   ]
 description = "Natural Language Understanding (text processing) for math symbols, digits, and words with a Gradio user interface and REST API."
 readme = "README.md"
-requires-python = ">=3.7"
-license = {file = "LICENSE.md"}
-classifiers = [
-    "Programming Language :: Python :: 3",
-#    "License :: OSI Approved :: MIT License",
-    "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
-    "Operating System :: OS Independent",
-]
 
-[dependencies]
+[tool.poetry.dependencies]
 python = "^3.7"
 editdistance = "*"
 gradio = "3.14.*"
@@ -33,14 +20,20 @@ pandas-gbq = "0.19.*"
 pytest = "7.2.*"
 python-dotenv = "0.21.*"
 scikit-learn = "^1.2"
+scikit-image = "^0.17"
 spacy = "3.4.*"
 torch = "1.12.*"
 transformers = "4.24.*"
 
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.2.1"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
 # [build-system]
 # requires = ["hatchling"]
 # build-backend = "hatchling.build"
 
-[tool.poetry.dev-dependencies]
-pytest = "^7.2"
-
+# repository = "https://gitlab.com/tangibleai/community/mathtext"

requirements.txt

@@ -1,10 +1,12 @@
-spacy==3.4.*
-pandas==1.5.*
-pandas-gbq==0.19.*
+editdistance
 gradio==3.14.*
-python-dotenv==0.21.*
-transformers==4.24.*
-torch==1.12.*
 httpx==0.23.*
 matplotlib==3.6.*
+pandas==1.5.*
+pandas-gbq==0.19.*
 pytest==7.2.*
+python-dotenv==0.21.*
+scikit-learn
+spacy==3.4.*
+torch==1.12.*
+transformers==4.24.*