andras/great-ai
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases 4 Packages Wiki Activity Actions

Add exception logging

Browse source
This commit is contained in:
Andras Schmelczer 2022-05-26 21:00:14 +02:00
parent 47e8d8b33a
commit cdc43f75ac
20 changed files with 144 additions and 182 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/simple/README.md
View file

@ -1,12 +0,0 @@
# Train Domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)
## Upload the dataset (or a part of it) to shared infrastructure
```sh
mkdir ss-data && cd ss-data
wget https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/manifest.txt
wget -B https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/ -i manifest.txt
cd -
python3 -m great_ai.open_s3 --secrets s3.ini --push ss-data
rm -rf ss-data
```

16
examples/simple/helpers.py
View file

@ -1,16 +0,0 @@
import re
from great_ai.utilities.clean import clean
from great_ai.utilities.lemmatize_text import lemmatize_text
def preprocess(text: str) -> str:
text = clean(text, convert_to_ascii=True)
text = re.sub(r"[^a-zA-Z0-9]", " ", text)
return text
def lemmatize(text: str) -> str:
lemmatized = lemmatize_text(text)
clean_lemmas = [re.sub(r"\d[\d.,]*", "NUM", lemma) for lemma in lemmatized]
return " ".join(clean_lemmas)

77
examples/simple/predict_domain.py
View file

@ -1,77 +0,0 @@
from typing import Dict, Iterable, List
from great_ai import GreatAI, use_model
from pydantic import BaseModel
from sklearn.pipeline import Pipeline
from helpers import lemmatize, preprocess
class DomainPrediction(BaseModel):
domain: str
probability: float
explanation: List[str]
@GreatAI.deploy()
@use_model("small-domain-prediction-v2", version="latest")
def predict_domain(
text: str, model: Pipeline, cut_off_probability: float = 0.2
) -> List[DomainPrediction]:
"""
Predict the scientific domain of the input text.
Return labels until their sum likelihood is larger than cut_off_probability.
"""
assert 0 <= cut_off_probability <= 1
text = preprocess(text)
feature_names = model.named_steps["vectorizer"].get_feature_names_out()
token_mapping = {lemmatize(original): original for original in text.split(" ")}
features = model.named_steps["vectorizer"].transform(
[" ".join(token_mapping.keys())]
)
prediction = model.named_steps["classifier"].predict_proba(features)[0]
best_classes = sorted(enumerate(prediction), key=lambda v: v[1], reverse=True)
results: List[DomainPrediction] = []
for class_index, probability in best_classes:
weights = model.named_steps["classifier"].feature_log_prob_[class_index]
domain = model.named_steps["classifier"].classes_[class_index]
results.append(
DomainPrediction(
domain=domain,
probability=round(probability * 100),
explanation=_get_explanation(
feature_names=feature_names,
features=features.A[0],
weights=weights,
token_mapping=token_mapping,
),
)
)
if sum(r.probability for r in results) >= cut_off_probability * 100:
break
return results
def _get_explanation(
feature_names: Iterable[str],
features: Iterable[float],
weights: Iterable[float],
token_mapping: Dict[str, str],
) -> List[str]:
influential = [
(weight, name)
for weight, value, name in zip(weights, features, feature_names)
if value
]
most_influential = sorted(influential, reverse=True)[:5]
return [token_mapping[name] for _, name in most_influential]

269
examples/simple/train.ipynb
View file

@ -1,269 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Train domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import matplotlib.pyplot as plt\n",
"from pathlib import Path\n",
"import pandas as pd\n",
"from sklearn import metrics, set_config\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.naive_bayes import MultinomialNB\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"from sklearn.model_selection import GridSearchCV\n",
"\n",
"from great_ai.utilities.parallel_map import parallel_map\n",
"from great_ai.utilities.language import is_english, predict_language\n",
"from great_ai import save_model, configure, LargeFile\n",
"\n",
"from helpers import preprocess, lemmatize"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configuration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"PREFIX = \"domain-\"\n",
"DATASET_KEY = \"data\"\n",
"MAX_FILE_COUNT = 5\n",
"MODEL_KEY = \"small-domain-prediction-v2\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"configure()\n",
"corpus_path = LargeFile(DATASET_KEY).get()\n",
"\n",
"set_config(display=\"diagram\")\n",
"plt.rcParams[\"figure.figsize\"] = (30, 15)\n",
"plt.rcParams[\"figure.facecolor\"] = \"white\"\n",
"plt.rcParams[\"font.size\"] = 12\n",
"plt.rcParams[\"axes.xmargin\"] = 0"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Preprocessing"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def clean_file(p: Path) -> None:\n",
" try:\n",
" processed_path = p.with_name(f\"{PREFIX}{p.stem}{p.suffix}\")\n",
"\n",
" if processed_path.exists():\n",
" return\n",
"\n",
" with open(p) as f:\n",
" content = json.load(f)\n",
"\n",
" result = {\n",
" lemmatize(preprocess(f'{c[\"title\"]} {c[\"abstract\"]}')): c[\"domain\"]\n",
" for c in content\n",
" if (\n",
" c[\"domain\"]\n",
" and c[\"abstract\"]\n",
" and is_english(predict_language(c[\"abstract\"]))\n",
" )\n",
" }\n",
"\n",
" with open(processed_path, \"w\") as f:\n",
" json.dump(result, f)\n",
" except Exception as e:\n",
" print(f\"Error ({e}) processing {p}\")\n",
"\n",
"\n",
"parallel_map(\n",
" clean_file,\n",
" list(corpus_path.glob(\"s2-corpus-*.json\"))[:MAX_FILE_COUNT],\n",
" chunk_size=1,\n",
")\n",
"None"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"corpora = list(corpus_path.glob(f\"{PREFIX}*.json\"))[:MAX_FILE_COUNT]\n",
"print(f\"Found {len(corpora)} files\")\n",
"\n",
"data = []\n",
"for p in corpora:\n",
" with open(p) as f:\n",
" data.extend(json.load(f).items())\n",
"\n",
"print(f\"Found {len(data)} documents\")\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(\n",
" [d[0] for d in data], [d[1] for d in data], test_size=0.1, random_state=1\n",
")\n",
"\n",
"X_train = [x for x, y in zip(X_train, y_train) for domain in y]\n",
"y_train = [domain for x, y in zip(X_train, y_train) for domain in y]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Optimise and train Multinomial Naive Bayes classifier"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def create_pipeline() -> Pipeline:\n",
" return Pipeline(\n",
" steps=[\n",
" (\"vectorizer\", TfidfVectorizer()),\n",
" (\"classifier\", MultinomialNB()),\n",
" ]\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"optimisation_pipeline = GridSearchCV(\n",
" create_pipeline(),\n",
" {\n",
" \"vectorizer__max_df\": [0.05, 0.1],\n",
" \"vectorizer__min_df\": [5, 20],\n",
" \"vectorizer__sublinear_tf\": [True, False],\n",
" \"classifier__alpha\": [0.5, 1],\n",
" \"classifier__fit_prior\": [True, False],\n",
" },\n",
" scoring=\"f1_macro\",\n",
" cv=3,\n",
" n_jobs=8,\n",
" verbose=1,\n",
")\n",
"optimisation_pipeline.fit(X_train, y_train)\n",
"\n",
"results = pd.DataFrame(optimisation_pipeline.cv_results_)\n",
"results.sort_values(\"rank_test_score\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"classifier = create_pipeline()\n",
"classifier.set_params(**optimisation_pipeline.best_params_)\n",
"classifier.fit(X_train, y_train)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Check accuracy on the test split"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"predicted = classifier.predict(X_test)\n",
"\n",
"y_test_aligned = [p if p in y else y[0] for p, y in zip(predicted, y_test)]\n",
"\n",
"print(metrics.classification_report(y_test_aligned, predicted))\n",
"metrics.ConfusionMatrixDisplay.from_predictions(\n",
" y_true=y_test_aligned,\n",
" y_pred=predicted,\n",
" xticks_rotation=\"vertical\",\n",
" normalize=\"pred\",\n",
" values_format=\".2f\",\n",
")\n",
"None"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Export the model using GreatAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"save_model(classifier, key=MODEL_KEY, keep_last_n=5)"
]
}
],
"metadata": {
"interpreter": {
"hash": "acc70e949538f42041ccc57bc4df2261507e3fd7d6b9ce5dcc28e3bcf9d48274"
},
"kernelspec": {
"display_name": "Python 3.8.5 ('.env': venv)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}