diff --git a/docs/pages/docs/config.md b/docs/pages/docs/config.md
index b8db7fc42..eb84c9797 100644
--- a/docs/pages/docs/config.md
+++ b/docs/pages/docs/config.md
@@ -37,7 +37,7 @@ tests:
from langtest import Harness
# Create test Harness with config file
-h = Harness(task='text-classification', model='path/to/local_saved_model', hub='spacy', data='test.csv', config='config.yml')
+h = Harness(task='text-classification', model={'model': 'path/to/local_saved_model', 'hub':'spacy'}, data={"data_source":'test.csv'}, config='config.yml')
```
#### Using the `.configure()` Method
@@ -46,7 +46,7 @@ h = Harness(task='text-classification', model='path/to/local_saved_model', hub='
from langtest import Harness
# Create test Harness without config file
-h = Harness(task='text-classification', model='path/to/local_saved_model', hub='spacy', data='test.csv')
+h = Harness(task='text-classification', model={'model': 'path/to/local_saved_model', 'hub':'spacy'}, data={"data_source":'test.csv'})
h.configure(
{
diff --git a/docs/pages/docs/data.md b/docs/pages/docs/data.md
index 500fc04c4..c743516d2 100644
--- a/docs/pages/docs/data.md
+++ b/docs/pages/docs/data.md
@@ -61,10 +61,9 @@ In the Harness, we specify the data input in the following way:
from langtest import Harness
harness = Harness(task='ner',
- model='en_core_web_sm',
- config='config.yml',
- hub='spacy',
- data='sample.conll') #Either of the two formats can be specified.
+ model={'model': 'en_core_web_sm', 'hub':'spacy'},
+ data={"data_source":'test.conll'},
+ config='config.yml') #Either of the two formats can be specified.
```
@@ -101,10 +100,9 @@ In the Harness, we specify the data input in the following way:
from langtest import Harness
harness = Harness(task='text-classification',
- model='mrm8488/distilroberta-finetuned-tweets-hate-speech',
- config='config.yml',
- hub ='huggingface',
- data='sample.csv')
+ model={'model': 'mrm8488/distilroberta-finetuned-tweets-hate-speech', 'hub':'huggingface'},
+ data={"data_source":'sample.csv'},
+ config='config.yml')
```
@@ -117,11 +115,12 @@ To handle text classification task for Hugging Face Datasets, the Harness class
```python
{
- "name": "",
+ "data_source": "",
"subset": "",
"feature_column": "",
"target_column": "",
- "split": ""
+ "split": "",
+ "source": "huggingface"
}
```
@@ -133,13 +132,14 @@ In the Harness, we specify the data input in the following way:
# Import Harness from the LangTest library
from langtest import Harness
-harness = Harness(task="text-classification", hub="huggingface",
- model="distilbert-base-uncased-finetuned-sst-2-english",
- data={"name":'glue',
+harness = Harness(task="text-classification",
+ model={'model': 'mrm8488/distilroberta-finetuned-tweets-hate-speech', 'hub':'huggingface'},
+ data={"data_source":'glue',
"subset":"sst2",
"feature_column":"sentence",
"target_column":'label',
- "split":"train"
+ "split":"train",
+ "source": "huggingface"
})
```
@@ -209,10 +209,9 @@ In the Harness, we specify the data input in the following way:
from langtest import Harness
harness = Harness(task='question-answering',
- model='gpt-3.5-turbo',
- config='config.yml',
- hub ='openai',
- data='BoolQ-test')
+ model={'model': 'text-davinci-003', 'hub':'openai'},
+ data={"data_source":'BoolQ-test'},
+ config='config.yml')
```
@@ -249,10 +248,9 @@ In the Harness, we specify the data input in the following way:
from langtest import Harness
harness = Harness(task='summarization',
- model='text-davinci-002',
- config='config.yml',
- hub ='openai',
- data='XSum-test-tiny')
+ model={'model': 'text-davinci-003', 'hub':'openai'},
+ data={"data_source":'XSum-test-tiny'},
+ config='config.yml')
```
#### Passing a Hugging Face Dataset for Summarization to the Harness
@@ -264,12 +262,12 @@ In the Harness, we specify the data input in the following way:
from langtest import Harness
harness = Harness(task="summarization",
- hub="openai",
- model="text-davinci-003",
- data={"name":'samsum',
+ model={'model': 'text-davinci-003', 'hub':'openai'},
+ data={"data_source":'samsum',
"feature_column":"dialogue",
"target_column":'summary',
- "split":"test"
+ "split":"test",
+ "source": "huggingface"
})
```
@@ -305,9 +303,8 @@ In the Harness, we specify the data input in the following way:
from langtest import Harness
harness = Harness(task='toxicity',
- model='text-davinci-002',
- hub='openai',
- data='toxicity-test-tiny')
+ model={'model': 'text-davinci-003', 'hub':'openai'},
+ data={"data_source":'toxicity-test-tiny'})
```
\ No newline at end of file
diff --git a/docs/pages/docs/generate.md b/docs/pages/docs/generate.md
index 8d5611c63..9486dcf4a 100644
--- a/docs/pages/docs/generate.md
+++ b/docs/pages/docs/generate.md
@@ -44,7 +44,7 @@ tests:
from langtest import Harness
# Create test Harness with config file
-h = Harness(task='text-classification', model='path/to/local_saved_model', hub='spacy', data='test.csv', config='config.yml')
+h = Harness(task='text-classification', model={'model': 'path/to/local_saved_model', 'hub':'spacy'}, data={"data_source":'test.csv'}, config='config.yml')
```
#### Using the `.configure()` Method
@@ -53,7 +53,7 @@ h = Harness(task='text-classification', model='path/to/local_saved_model', hub='
from langtest import Harness
# Create test Harness without config file
-h = Harness(task='text-classification', model='path/to/local_saved_model', hub='spacy', data='test.csv')
+h = Harness(task='text-classification', model={'model': 'path/to/local_saved_model', 'hub':'spacy'}, data={"data_source":'test.csv'})
h.configure(
{
diff --git a/docs/pages/docs/generate_augmentation.md b/docs/pages/docs/generate_augmentation.md
index 382e64c8b..fe8684b67 100644
--- a/docs/pages/docs/generate_augmentation.md
+++ b/docs/pages/docs/generate_augmentation.md
@@ -85,7 +85,8 @@ data_kwargs = {
"subset": "sst2",
"feature_column": "sentence",
"target_column": "label",
- "split": "train"
+ "split": "train",
+ "source": "huggingface"
}
h.augment(
diff --git a/docs/pages/tutorials/tutorials.md b/docs/pages/tutorials/tutorials.md
index f85632076..8919cfe7c 100644
--- a/docs/pages/tutorials/tutorials.md
+++ b/docs/pages/tutorials/tutorials.md
@@ -52,7 +52,7 @@ The following table gives an overview of the different tutorial notebooks. We ha
|NQ open |OpenAI |Question-Answering |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/NQ_open_dataset.ipynb)|
|BoolQ |OpenAI |Question-Answering |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/BoolQ_dataset.ipynb)|
|XSum |OpenAI |Summarization |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/XSum_dataset.ipynb)|
-|HuggingFaceDataset-Support |Hugging Face/OpenAI |Text-Classification/Summarization |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/HuggingFace_Dataset_Notebook.ipynb)|
+|HuggingFaceDataset-Support |Hugging Face/OpenAI |Text-Classification/NER/Summarization |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/HuggingFace_Dataset_Notebook.ipynb)|
|Augmentation-Control |/John Snow Labs |NER |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Augmentation_Control_Notebook.ipynb)|
|Comparing Models |Hugging Face/John Snow Labs/Spacy |NER/Text-Classification |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Comparing_Models_Notebook.ipynb)|
|Runtime Test |Hugging Face/John Snow Labs/Spacy |NER |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/RuntimeTest_Notebook.ipynb)|
@@ -62,7 +62,7 @@ The following table gives an overview of the different tutorial notebooks. We ha
|Templatic-Augmentation |John Snow Labs |NER |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Templatic_Augmentation_Notebook.ipynb)|
|Clinical-Tests-Notebook |OpenAI |Clinical-Tests |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/Clinical_Tests.ipynb)|
|Prompt-Injection-Notebook |OpenAI |Security |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/Prompt_Injections_Tests.ipynb)|
-
+|Loading-Data-with-Custom-Columns |Hugging Face/OpenAI |NER/Text-Classification/Question-Answering/Summarization |[](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/custom_column_csv.ipynb)|