Merge pull request #44 from aimakerspace/asgcn

Add Sentic-GCN to SGNlp

.gitlab-ci.yml

@@ -16,6 +16,8 @@ cache:
 
 run_non_slow_unit_tests:
   stage: unit_test_non_slow
+  tags:
+    - dind
   before_script:
     - python -m venv .venv
     - source .venv/bin/activate
@@ -29,6 +31,8 @@ run_non_slow_unit_tests:
 
 run_slow_unit_tests:
   stage: unit_test_slow
+  tags:
+    - dind
   when: manual
   before_script:
     - python -m venv .venv
@@ -45,6 +49,8 @@ run_slow_unit_tests:
 
 generate_demo_api_yaml:
   stage: pre
+  tags:
+    - dind
   image: alpine:latest
   script:
     - apk add -U jsonnet
@@ -55,6 +61,8 @@ generate_demo_api_yaml:
 
 generate_dev_demo_api_yaml:
   stage: pre
+  tags:
+    - dind
   image: alpine:latest
   script:
     - apk add -U jsonnet

demo_api/sentic_gcn/Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.8-buster
+
+COPY . /demo_api
+
+WORKDIR /demo_api/sentic_gcn
+
+RUN pip install -r requirements.txt
+RUN python -m download_pretrained
+
+CMD PYTHONPATH=../../ gunicorn -c ../gunicorn.conf.py

demo_api/sentic_gcn/api.py

@@ -0,0 +1,46 @@
+from flask import request, jsonify
+
+from demo_api.common import create_api
+from sgnlp.models.sentic_gcn import (
+    SenticGCNBertModel,
+    SenticGCNBertConfig,
+    SenticGCNBertPreprocessor,
+    SenticGCNBertPostprocessor,
+)
+
+app = create_api(app_name=__name__, model_card_path="model_card/sentic_gcn.json")
+
+preprocessor = SenticGCNBertPreprocessor(
+    senticnet="https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticnet.pickle", device="cpu"
+)
+
+postprocessor = SenticGCNBertPostprocessor()
+
+# Load model
+config = SenticGCNBertConfig.from_pretrained(
+    "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/config.json"
+)
+
+model = SenticGCNBertModel.from_pretrained(
+    "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/pytorch_model.bin", config=config
+)
+
+app.logger.info("Preprocessing pipeline and model initialization complete.")
+
+
+@app.route("/predict", methods=["POST"])
+def predict():
+    req_body = request.get_json()
+
+    # Preprocessing
+    processed_inputs, processed_indices = preprocessor([req_body])
+    outputs = model(processed_indices)
+
+    # Postprocessing
+    post_outputs = postprocessor(processed_inputs=processed_inputs, model_outputs=outputs)
+
+    return jsonify(post_outputs[0])
+
+
+if __name__ == "__main__":
+    app.run()

demo_api/sentic_gcn/dev.Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.8-buster
+
+COPY ./demo_api /demo_api
+COPY ./sgnlp /sgnlp
+COPY ./setup.py /setup.py
+COPY ./README.md /README.md
+
+RUN pip install -r /demo_api/sentic_gcn/requirements_dev.txt
+
+WORKDIR /demo_api/sentic_gcn
+
+RUN python -m download_pretrained
+
+CMD PYTHONPATH=../../ gunicorn -c ../gunicorn.conf.py

demo_api/sentic_gcn/download_pretrained.py

@@ -0,0 +1,22 @@
+"""Run this script during build time to download the pretrained models and relevant files first"""
+
+from sgnlp.models.sentic_gcn import (
+    SenticGCNConfig,
+    SenticGCNBertTokenizer,
+    SenticGCNBertModel,
+    SenticGCNBertPreprocessor
+)
+
+# Downloads preprocessor, pretrained config, tokenizer, model
+preprocessor = SenticGCNBertPreprocessor(
+    senticnet='https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticnet.pickle', 
+    device='cpu'
+)
+tokenizer = SenticGCNBertTokenizer.from_pretrained("bert-base-uncased")
+config = SenticGCNConfig.from_pretrained(
+    "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/config.json"
+)
+model = SenticGCNBertModel.from_pretrained(
+    "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/pytorch_model.bin", 
+    config=config
+)

demo_api/sentic_gcn/model_card/sentic_gcn.json

@@ -0,0 +1,44 @@
+{
+    "name": "Sentic GCN",
+    "languages": "English",
+    "description": "This is a neural network that utilises LSTM and GCN to detect the sentiment polarities of different aspects in the same sentence. The models used corresponds to the associated models described in the paper.",
+    "paper": {
+      "text": "Bin Liang, Hang Su, Lin Gui, Erik Cambria, Ruifeng Xu. (2021). Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks, 2021: 107643.",
+      "url": "https://github.com/BinLiang-NLP/Sentic-GCN"
+    },
+    "trainingDataset": {
+      "text": "acl-14-short-data, semeval14, semeval15, semeval16",
+      "url": "https://github.com/BinLiang-NLP/Sentic-GCN/tree/main/datasets"
+    },
+    "evaluationDataset": {
+      "text": "acl-14-short-data, semeval14, semeval15, semeval16",
+      "url": "https://github.com/BinLiang-NLP/Sentic-GCN/tree/main/datasets"
+    },
+    "evaluationScores": "Sentic-GCN: 94.36% Acc, 94.43% F1 (SemEval14-Laptop), 94.55% Acc, 91.99% F1 (SemEval14-Restaurant), 95.02% Acc, 93.22% F1 (SemEval15-Restaurant), 96.75% Acc, 93.55% F1 (SemEval16-Restaurant). Sentic-GCN Bert: 99.22% Acc, 99.15% F1 (SemEval14-Laptop), 97.39% Acc, 96.53% F1 (SemEval14-Restaurant), 99.17% Acc, 98.78% F1 (SemEval15-Restaurant), 99.37% Acc, 98.79% F1 (SemEval16-Restaurant).",
+    "trainingConfig": {
+      "text": "Refer to documentation for details."
+    },
+    "trainingTime": "Sentic-GCN:  ~10 mins for ~35 epochs (early stopped),  Sentic-GCN Bert:  ~1 hr for ~40 epochs (early stopped) for SemEval14-Laptop/SemEval14-Restaurant/SemEval15-Restaurant/SemEval16-Restaurant datasets.",
+    "modelWeights": {
+      "text": "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/pytorch_model.bin",
+      "url": "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/pytorch_model.bin"
+    },
+    "modelConfig": {
+      "text": "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/config.json",
+      "url": "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/config.json"
+    },
+    "modelInput": "Aspect (word), sentence containing the aspect",
+    "modelOutput": "Sentiment of aspect, -1 (negative), 0 (neutral), 1 (postive)",
+    "modelSize": "Sentic-GCN: ~8.7MB, Sentic-GCN Bert: ~7.1MB",
+    "inferenceInfo": "< 1 sec on Intel(R) i7 Quad-Core @ 1.7GHz.",
+    "usageScenarios": "Sentiment analysis of aspects in sentences",
+    "originalCode": {
+      "text": "https://github.com/BinLiang-NLP/Sentic-GCN",
+      "url": "https://github.com/BinLiang-NLP/Sentic-GCN"
+    },
+    "license": {
+      "text": "MIT License",
+      "url": "https://choosealicense.com/licenses/mit"
+    },
+    "contact": "[email protected]"
+  }

demo_api/sentic_gcn/requirements.txt

@@ -0,0 +1,6 @@
+torch==1.10.1
+spacy==3.2.1
+numpy==1.22.0
+flask
+gunicorn
+sgnlp

demo_api/sentic_gcn/requirements_dev.txt

@@ -0,0 +1,6 @@
+-e .
+torch==1.10.1
+spacy==3.2.1
+numpy==1.22.0
+flask
+gunicorn

demo_api/sentic_gcn/usage.py

@@ -0,0 +1,43 @@
+from sgnlp.models.sentic_gcn import (
+    SenticGCNBertModel,
+    SenticGCNBertPreprocessor,
+    SenticGCNBertConfig,
+    SenticGCNBertPostprocessor,
+)
+
+preprocessor = SenticGCNBertPreprocessor(
+    senticnet="https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticnet.pickle", device="cpu"
+)
+
+postprocessor = SenticGCNBertPostprocessor()
+
+# Load model
+config = SenticGCNBertConfig.from_pretrained(
+    "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/config.json"
+)
+
+model = SenticGCNBertModel.from_pretrained(
+    "https://storage.googleapis.com/sgnlp/models/sentic_gcn/senticgcn_bert/pytorch_model.bin", config=config
+)
+
+# Inputs
+inputs = [
+    {
+        "aspects": ["service", "decor"],
+        "sentence": "Everything is always cooked to perfection , the service is excellent, the decor cool and understated.",
+    },
+    {
+        "aspects": ["food", "portions"],
+        "sentence": "The food was lousy - too sweet or too salty and the portions tiny.",
+    },
+    {
+        "aspects": ["service"],
+        "sentence": "To sum it up : service varies from good to mediorce , depending on which waiter you get ; generally it is just average ok .",
+    },
+]
+
+processed_inputs, processed_indices = preprocessor(inputs)
+outputs = model(processed_indices)
+
+# Postprocessing
+post_outputs = postprocessor(processed_inputs=processed_inputs, model_outputs=outputs)