Documentation fixes and refurbishing [GSK-2144, GSK-2145, GSK-2146, GSK-2150].

docs/getting_started/quickstart/quickstart_nlp.ipynb

@@ -49,7 +49,7 @@
    },
    "outputs": [],
    "source": [
-    "! pip install giskard --upgrade"
+    "%pip install giskard --upgrade"
    ]
   },
   {
@@ -329,7 +329,8 @@
    "metadata": {},
    "source": [
     "If you are running in a notebook, you can display the scan report directly in the notebook using `display(...)`, otherwise you can export the report to an HTML file. Check the [API Reference](https://docs.giskard.ai/en/latest/reference/scan/report.html#giskard.scanner.report.ScanReport) for more details on the export methods available on the `ScanReport` class."
-   ]
+   ],
+   "id": "9dd5baaaa6a7ee62"
   },
   {
    "cell_type": "code",

docs/getting_started/quickstart/quickstart_tabular.ipynb

@@ -49,7 +49,7 @@
    },
    "outputs": [],
    "source": [
-    "! pip install giskard --upgrade"
+    "%pip install giskard --upgrade"
    ]
   },
   {
@@ -294,7 +294,8 @@
    "metadata": {},
    "source": [
     "If you are running in a notebook, you can display the scan report directly in the notebook using `display(...)`, otherwise you can export the report to an HTML file. Check the [API Reference](https://docs.giskard.ai/en/latest/reference/scan/report.html#giskard.scanner.report.ScanReport) for more details on the export methods available on the `ScanReport` class."
-   ]
+   ],
+   "id": "28272f36e73f8a76"
   },
   {
    "cell_type": "code",

docs/open_source/customize_tests/data_slices/index.md

@@ -12,7 +12,7 @@ This section explains how to create your own slicing function, or customize the
 
 The [Giskard catalog](../../catalogs/slicing-function-catalog/index.rst) provides you with different slicing functions for NLP such as sentiment, hate, and toxicity detectors:
 
-```
+```python
 #Load sentiment analysis model from the Giskard catalog
 from giskard.ml_worker.testing.functions.slicing import positive_sentiment_analysis
 ```
@@ -27,17 +27,20 @@ To create a Giskard slicing function, you just need to decorate an existing Pyth
 
 When `row_level=True`, you can decorate a function that takes a pandas dataframe **row** as input and returns a boolean. Make sure that the first argument of your function corresponds to the row you want to filter:
 
-```
-from giskard import slicing_function, demo
+```python
 import pandas as pd
+from giskard import slicing_function, demo, Dataset
+
 
 _, df = demo.titanic()
 dataset = Dataset(df=df, target="Survived", cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"])
 
+
 @slicing_function(row_level=True)
 def my_func2(row: pd.Series, threshold: int):
     return row['Age'] > threshold
 
+
 dataset.slice(my_func2(threshold=20))
 ```
 
@@ -47,18 +50,21 @@ dataset.slice(my_func2(threshold=20))
 
 When `row_level=False`, you can decorate a function that takes a full **pandas dataframe** as input and returns a filtered pandas dataframe. Make sure that the first argument of your function corresponds to the pandas dataframe you want to filter:
 
-```
-from giskard import slicing_function, demo
+```python
+from giskard import slicing_function, demo, Dataset
 import pandas as pd
 
+
 _, df = demo.titanic()
 dataset = Dataset(df=df, target="Survived", cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"])
 
+
 @slicing_function(row_level=False)
 def my_func1(df: pd.DataFrame, threshold: int):
     df['Age'] = df['Age'] > threshold
     return df
 
+
 dataset.slice(my_func1(threshold=20))
 ```
 
@@ -68,18 +74,20 @@ dataset.slice(my_func1(threshold=20))
 
 When `cell_level=True` (False by default), you can decorate a function that takes a **value** (string, numeric or text) as an argument and returns a boolean. Make sure that the first argument of your function corresponds to the value and that the second argument defines the **column name** where you want to filter the value:
 
-```
-from giskard import slicing_function, demo
-import pandas as pd
+```python
+from giskard import slicing_function, demo, Dataset
+
 
 _, df = demo.titanic()
 dataset = Dataset(df=df, target="Survived", cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"])
 
+
 @slicing_function(cell_level=True)
 def my_func3(cell: int, threshold: int):
-    return cell>threshold
+    return cell > threshold
+
 
-train_df.slice(my_func3(threshold=20), column_name='Age')
+dataset.slice(my_func3(threshold=20), column_name='Age')
 ```
 
 ::::
@@ -89,7 +97,11 @@ train_df.slice(my_func3(threshold=20), column_name='Age')
 
 Slicing functions can be very powerful to detect complex behaviour when they are used as fixtures inside your test suite. With the Giskard framework you can easily create complex slicing functions. For instance:
 
-```
+```python
+import pandas as pd
+from giskard import slicing_function
+
+
 def _sentiment_analysis(x, column_name, threshold, model, emotion):
     from transformers import pipeline
     sentiment_pipeline = pipeline("sentiment-analysis", model=model)
@@ -98,6 +110,7 @@ def _sentiment_analysis(x, column_name, threshold, model, emotion):
     return x.iloc[list(
         map(lambda s: s['label'] == emotion and s['score'] >= threshold, sentiment_pipeline(sentences)))]
 
+
 @slicing_function(name="Emotion sentiment", row_level=False, tags=["sentiment", "text"])
 def emotion_sentiment_analysis(x: pd.DataFrame, column_name: str, emotion: str, threshold: float = 0.9) -> pd.DataFrame:
     """
@@ -110,15 +123,16 @@ def emotion_sentiment_analysis(x: pd.DataFrame, column_name: str, emotion: str,
 
 Giskard enables you to automatically generate the slicing functions that are the most insightul for your ML models. You can easily extract the results of the [scan feature](../scan/index.rst) using the following code:
 
-```
-from giskard import Dataset, Model
+```python
+from giskard import Dataset, Model, scan
+
 
 my_dataset = Dataset(...)
 my_model = Model(...)
 
-scan_result = giskard.scan(my_model, my_dataset)
+scan_result = scan(my_model, my_dataset)
 test_suite = scan_result.generate_test_suite("My first test suite")
-test_suite.run()[1]
+test_suite.run()
 ```
 
 ## Upload your slicing function to the Giskard hub

docs/open_source/customize_tests/data_transformations/index.md

@@ -11,8 +11,8 @@ This section explains how to create your own transformation function, or customi
 
 The [Giskard catalog](../../catalogs/transformation-function-catalog/index.rst) provides you with different transformation functions for NLP use cases such as *adding typos*, or *punctuation stripping*.
 
-```
-#Import keyboard typo transformations
+```python
+# Import keyboard typo transformations
 from giskard.ml_worker.testing.functions.transformation import keyboard_typo_transformation
 ```
 
@@ -26,18 +26,21 @@ To create a Giskard transformation function, you just need to decorate an existi
 
 When `row_level=True`, you can decorate a function that takes a pandas dataframe **row** as input, and returns a boolean. Make sure that the first argument of your function corresponds to the row you want to filter:
 
-```
-from giskard import transformation_function, demo
+```python
 import pandas as pd
+from giskard import transformation_function, demo, Dataset
+
 
 _, my_df = demo.titanic()
 dataset = Dataset(df=my_df, target="Survived", cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"])
 
+
 @transformation_function(row_level=True)
 def my_func2(row: pd.Series, offset: int):
     row['Age'] = row['Age'] + offset
     return row
 
+
 transformed_dataset = dataset.transform(my_func2(offset=20))
 ```
 
@@ -47,18 +50,21 @@ transformed_dataset = dataset.transform(my_func2(offset=20))
 
 When `row_level=False`, you can decorate a function that takes a full **pandas dataframe** as input, and returns a filtered pandas dataframe. Make sure that the first argument of your function corresponds to the pandas dataframe you want to filter:
 
-```
-from giskard import transformation_function, demo
+```python
 import pandas as pd
+from giskard import transformation_function, demo, Dataset
+
 
 _, df = demo.titanic()
 dataset = Dataset(df=df, target="Survived", cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"])
 
+
 @transformation_function(row_level=False)
 def my_func1(df: pd.DataFrame, offset: int):
     df['Age'] = df['Age'] + offset
     return df
 
+
 transformed_dataset = dataset.transform(my_func1(offset=20))
 ```
 
@@ -68,17 +74,19 @@ transformed_dataset = dataset.transform(my_func1(offset=20))
 
 When `cell_level=True` (False by default), you can decorate a function that takes as argument a **value** (string, numeric or text), and returns a boolean. Make sure that the first argument of your function corresponds to the value, and that the second argument defines the **column name** where you want to filter the value:
 
-```
-from giskard import transformation_function, demo
-import pandas as pd
+```python
+from giskard import transformation_function, demo, Dataset
+
 
 _, df = demo.titanic()
 dataset = Dataset(df=df, target="Survived", cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"])
 
+
 @transformation_function(cell_level=True)
 def my_func3(cell: int, offset: int):
     return cell + offset
 
+
 transformed_dataset = dataset.transform(my_func3(offset=20), column_name='Age')
 ```
 
@@ -89,11 +97,22 @@ transformed_dataset = dataset.transform(my_func3(offset=20), column_name='Age')
 
 Transformation functions can be very powerful to detect complex behaviour when they are used as fixtures inside your test suite. With the Giskard framework you can easily create complex transformation functions. For example:
 
-```
+```python
+import os
+import pandas as pd
+from giskard import transformation_function
+
+
 @transformation_function(name="Change writing style", row_level=False, tags=['text'])
-def change_writing_style(x: pd.DataFrame, index: int, column_name: str, style: str,
-                         OPENAI_API_KEY: str) -> pd.DataFrame:
-    os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+def change_writing_style(
+        x: pd.DataFrame,
+        index: int,
+        column_name: str,
+        style: str,
+        openai_api_key: str
+) -> pd.DataFrame:
+    os.environ["OPENAI_API_KEY"] = openai_api_key
+
     rewrite_prompt_template = """
     As a text rewriting robot, your task is to rewrite a given text using a specified rewriting style. You will receive a prompt with the following format:
     ```
@@ -115,10 +134,9 @@ def change_writing_style(x: pd.DataFrame, index: int, column_name: str, style: s
     ```
     """
 
-    from langchain import PromptTemplate
-    from langchain import LLMChain
-    from langchain import OpenAI
+    from langchain import PromptTemplate, LLMChain, OpenAI
 
+
     rewrite_prompt = PromptTemplate(input_variables=['text', 'style'], template=rewrite_prompt_template)
     chain_rewrite = LLMChain(llm=OpenAI(), prompt=rewrite_prompt)
 
@@ -129,15 +147,16 @@ def change_writing_style(x: pd.DataFrame, index: int, column_name: str, style: s
 
 Giskard enables you to automatically generate the transformation functions that are the most insightul for your ML models. You can easily extract the results of the [scan feature](../scan/index.rst) using the following code:
 
-```
-from giskard import Dataset, Model
+```python
+from giskard import Dataset, Model, scan
+
 
 my_dataset = Dataset(...)
 my_model = Model(...)
 
-scan_result = giskard.scan(my_model, my_dataset)
+scan_result = scan(my_model, my_dataset)
 test_suite = scan_result.generate_test_suite("My first test suite")
-test_suite.run()[1]
+test_suite.run()
 ```
 
 ## Save your transformation function