A thread on AUC Score (Area under the ROC Curve) Interpretation in #DataScience #MachineLearning

1/16

#DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas

1/16

#DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas

2/16

"roc_auc_score" is defined as the area under the ROC curve, which is the curve having False Positive Rate on the x-axis and True Positive Rate on the y-axis at all classification thresholds.

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python

"roc_auc_score" is defined as the area under the ROC curve, which is the curve having False Positive Rate on the x-axis and True Positive Rate on the y-axis at all classification thresholds.

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python

3/16

AUC ranges in value from 0 to 1.

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas #Stat #dataviz #learning

AUC ranges in value from 0 to 1.

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas #Stat #dataviz #learning

How to Create Small Multiple Charts in Python, with Plotly

🧵[1/23]

sharpsightlabs.com/blog/plotly-sm…

#python #datascience #pythoncode #datavisualization

🧵[1/23]

sharpsightlabs.com/blog/plotly-sm…

#python #datascience #pythoncode #datavisualization

[2/]

Before I get into the mechanics of how to create a small multiple charts in Python, let me quickly explain why they are so important.

Before I get into the mechanics of how to create a small multiple charts in Python, let me quickly explain why they are so important.

[3/]

Small multiple charts are one of my favorite chart types.

They are very powerful, and also highly under-used.

#datascience #dataanalytics #datavisualization

Small multiple charts are one of my favorite chart types.

They are very powerful, and also highly under-used.

#datascience #dataanalytics #datavisualization

In Python ...

You can combine Numpy arrays vertically or horizontally using np.concatenate

#Python #pythoncode #datascience

You can combine Numpy arrays vertically or horizontally using np.concatenate

#Python #pythoncode #datascience

The first argument to the function is a list (or collection) of arrays that you want to combine.

You can actually combine many arrays ...just put them inside the list.

You can actually combine many arrays ...just put them inside the list.

The axis parameter controls the direction along which you combine the arrays.

For 2D arrays ...

'axis = 0' combines vertically

'axis = 1' combines horizontally

For 2D arrays ...

'axis = 0' combines vertically

'axis = 1' combines horizontally

In Matplotlib ...

You can get the RGBA representation of a color with the to_rgba() function.

#Python #pythoncode #datavisualization

You can get the RGBA representation of a color with the to_rgba() function.

#Python #pythoncode #datavisualization

You'll notice that the output of to_rgba is a tuple with four floats: (%red, %green, %blue, alpha)

#Python

#Python

In RGBA, the alpha channel represents the opacity of the color, where:

– 0.0 is fully transparent

– 1.0 is fully opaque

– 0.0 is fully transparent

– 1.0 is fully opaque

In Python, you can visualize images with the Plotly IMshow function.

🧵[1/8]

sharpsightlabs.com/blog/plotly-im…

#Python #pythonlearning #datascience #datavisualization

🧵[1/8]

sharpsightlabs.com/blog/plotly-im…

#Python #pythonlearning #datascience #datavisualization

[2/8]

You can use Plotly IMshow for a few uses.

You can use it to plot heatmaps ...

But you can also use it to plot images.

You can use Plotly IMshow for a few uses.

You can use it to plot heatmaps ...

But you can also use it to plot images.

[3/8]

The syntax for Plotly IMshow is pretty simple.

You call the function as px.imshow and then provide the name of the image file you want to visualize.

(This assumes you've imported Plotly express as px)

#Python #pythoncode

The syntax for Plotly IMshow is pretty simple.

You call the function as px.imshow and then provide the name of the image file you want to visualize.

(This assumes you've imported Plotly express as px)

#Python #pythoncode

In Python ...

You can use the Pandas dropna method to drop rows with missing values.

#Python #pythoncode #datascience

You can use the Pandas dropna method to drop rows with missing values.

#Python #pythoncode #datascience

As seen above, you can limit dropna to specific columns with the 'subset=' parameter.

With 'subset=', you can specify the columns in which dropna will look for missing values

#Python #pythonlearning #datascience

With 'subset=', you can specify the columns in which dropna will look for missing values

#Python #pythonlearning #datascience

If it finds missing values in any of those columns, it will drop the row.

But it will ignore missing values in other columns.

But it will ignore missing values in other columns.

In Python ...

You can use Numpy all to test conditions about the properties of a Numpy array.

#Python #pythoncode #datascience

You can use Numpy all to test conditions about the properties of a Numpy array.

#Python #pythoncode #datascience

☝️

So for instance, in the example above, I test if all of the values are greater than 2, by column.

#Python

So for instance, in the example above, I test if all of the values are greater than 2, by column.

#Python

To do this, you need to know how np.all works ...

But you also need to know how to use axes.

#Python #pythonlearning

But you also need to know how to use axes.

#Python #pythonlearning

Some super-useful magic commands for Jupyter notebook - A thread

1/n

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Datavisualization #programming #DataAnalytics #pythoncode #pythoncode #AI #pythonprogramming #pythonlearning #Data

1/n

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Datavisualization #programming #DataAnalytics #pythoncode #pythoncode #AI #pythonprogramming #pythonlearning #Data

2/n

Types of magic commands

Line magics - starts with % character. Rest of the line is its argument passed without parentheses or quotes.

Cell magics - %% - can operate on multiple lines below their call.

#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist

Types of magic commands

Line magics - starts with % character. Rest of the line is its argument passed without parentheses or quotes.

Cell magics - %% - can operate on multiple lines below their call.

#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist

3/n

%load - load code from an external source into a cell in Jupyter Notebook

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Datavisualization #programming #DataAnalytics #pythoncode #pythoncode #AI #pythonprogramming #pythonlearning

%load - load code from an external source into a cell in Jupyter Notebook

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Datavisualization #programming #DataAnalytics #pythoncode #pythoncode #AI #pythonprogramming #pythonlearning

A thread - All the basic #Matrix #Algebra you will need in #MachineLearning #DeepLearning

1/n

#DataScience #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas #Stat

1/n

#DataScience #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas #Stat

2/n

A matrix A is a rectangular array of scalars usually presented in the following form

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #Math #Data #AI #TensorFlow #programming #DataAnalytics #ArtificialIntelligence #Mathematics

A matrix A is a rectangular array of scalars usually presented in the following form

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #Math #Data #AI #TensorFlow #programming #DataAnalytics #ArtificialIntelligence #Mathematics

A thread on AUC Score Interpretation

1/16

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas #Stat #dataviz #learning

1/16

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Math #Data #DataAnalytics #pythoncode #AI #ArtificialIntelligence #TensorFlow #PyTorch #Pandas #Stat #dataviz #learning

2/16

roc_auc_score is defined as the area under the ROC curve, having False Positive Rate on the x-axis and True Positive Rate on the y-axis at all classification thresholds

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #Math

roc_auc_score is defined as the area under the ROC curve, having False Positive Rate on the x-axis and True Positive Rate on the y-axis at all classification thresholds

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #DataScientist #Statistics #Math

Image interpolation occurs when you resize or distort your image from one pixel grid to another.

1/n

#computervision #IMAGE #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #programming #Math #Stat #dataviz #DataAnalytics #AI #ArtificialIntelligence #data

1/n

#computervision #IMAGE #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #programming #Math #Stat #dataviz #DataAnalytics #AI #ArtificialIntelligence #data

Image interpolation works in two directions, and tries to achieve a best approximation of a pixel's intensity based on the values at surrounding pixels.

2/n

#computervision #IMAGE #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #programming #Math #Stat

2/n

#computervision #IMAGE #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #programming #Math #Stat

Image resizing is necessary when you need to increase or decrease the total number of pixels, whereas remapping can occur when you are correcting for lens distortion or rotating an image.

3/n

#computervision #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python

3/n

#computervision #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python

What is p-value

#DataScience #DeepLearning #MachineLearning #ComputerVision #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Data #DataAnalytics #pythoncode #AI #numpy #ArtificialIntelligence #PyTorch #TensorFlow #Pandas #programming #Math #Stat #dataviz

#DataScience #DeepLearning #MachineLearning #ComputerVision #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Data #DataAnalytics #pythoncode #AI #numpy #ArtificialIntelligence #PyTorch #TensorFlow #Pandas #programming #Math #Stat #dataviz

A P-value is the probability of obtaining an effect at least as extreme as the one in your sample data, assuming the truth of the null hypothesis

#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Data #DataAnalytics #AI #Math

#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Data #DataAnalytics #AI #Math

P values address only one question:

How likely are your data, assuming a true null hypothesis ?

#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Data #DataAnalytics #AI #Math #Stat #Python #learning #LearnToCode

How likely are your data, assuming a true null hypothesis ?

#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist #Statistics #programming #Data #DataAnalytics #AI #Math #Stat #Python #learning #LearnToCode

#Learn 🧠🐍#python: Sometimes when programming in python they're situations when you want to copy the contents of an existing list into another. Python has several ways of achieving that. In this thread you will learn different ways of achieving that with the help of examples.

1) Using the equal (=) sign operator:

Using = operator you can copy the contents of an existing list onto another/new list. But there's a problem with this method which I will explain on the next section.

Using = operator you can copy the contents of an existing list onto another/new list. But there's a problem with this method which I will explain on the next section.

The problem with the above method is that if you modify the new copied_fruits list the original list (fruits) is modified too, this is because the copied list (copied_fruits) is referencing/ pointing to same fruits list in memory.