Madhurig at 07:32, 11 July 2025

2025-07-11T07:32:48Z

Madhurig at 07:13, 11 July 2025

2025-07-11T07:13:55Z

Nirmala Venkat: Created page with "
{| border="1" |- || '''Visual Cue''' || '''Narration''' |- |- style="border:0.5pt solid #000000;padding-top:0cm;pad..."

2025-06-24T11:13:01Z

Created page with " <div style="margin-left:1.27cm;margin-right:0cm;"></div> {| border="1" |- || '''Visual Cue''' || '''Narration''' |- |- style="border:0.5pt solid #000000;padding-top:0cm;pad..."

New page

<div style="margin-left:1.27cm;margin-right:0cm;"></div>
{| border="1"
|-
|| '''Visual Cue'''
|| '''Narration'''
|-
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.191cm;padding-right:0.191cm;"
|| <div style="color:#000000;">Show slide:</div>

'''Welcome'''
|| Welcome to the Spoken Tutorial on '''Logistic Regression - Multiclass Classification.'''
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''Learning Objectives'''
|| In this tutorial, we will learn about
* <div style="margin-left:1.27cm;margin-right:0cm;">Multiclass Classification for Logistic Regression</div>

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''System Requirements'''
|| To record this tutorial, I am using
* <div style="margin-left:1.27cm;margin-right:0cm;">'''Ubuntu Linux '''OS version''' 24.04'''</div>
* <div style="margin-left:1.27cm;margin-right:0cm;">'''Jupyter Notebook '''IDE</div>

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''Prerequisite'''
|| To follow this tutorial,
* <div style="margin-left:1.27cm;margin-right:0cm;">The learner must have basic knowledge of '''Python.'''</div>
* <div style="margin-left:1.27cm;margin-right:0cm;">For pre-requisite '''Python''' tutorials, please visit this website.</div>

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''Code files'''
||
* <div style="margin-left:1.27cm;margin-right:0cm;">The files used in this tutorial are provided in the '''Code files '''link.</div>
* <div style="margin-left:1.27cm;margin-right:0cm;">Please download and extract the files.</div>
* <div style="margin-left:1.27cm;margin-right:0cm;">Make a copy and then use them while practicing.</div>

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''Iris flower classification'''
|| To implement the '''Multiclass classification model '''we will,
* <div style="margin-left:1.27cm;margin-right:0cm;">Use the '''iris '''dataset to classify the '''iris '''flower.</div>
* <div style="margin-left:1.27cm;margin-right:0cm;"><span style="color:#000000;">To know more about the </span><span style="color:#000000;">'''iris'''</span><span style="color:#000000;"> dataset please watch </span>earlier <span style="color:#000000;">tutorials.</span></div>

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Point to the '''LR_Multiclass.ipynb'''
|| '''LR_Multiclass dot ipynb '''is the ipython notebook file created for this demonstration.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Press '''Ctrl+Alt'''+'''T '''keys

Type '''conda activate ml'''
Press '''Enter'''
Highlight: '''(ml)'''
|| Let us open the Linux terminal by pressing '''Ctrl, Alt''' and '''T '''keys together.

Activate the machine learning environment as shown.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Type '''cd Downloads'''

Type '''jupyter notebook'''

Press '''Enter '''
|| I have saved my code file in the '''Downloads''' folder.

Please navigate to the respective folder of your code file location.

Then type, '''jupyter space notebook '''and press''' Enter.'''
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show Jupyter Notebook Home page:

Double Click on '''LR_Multiclass.ipynb '''file
|| We can see the '''Jupyter Notebook''' '''Home page''' has opened in the web browser.

Click on the''' LR underscore Multiclass dot ipynb '''file to open it.

<div style="color:#000000;">Note that each cell will have the output displayed in this file.</div>

Let us see the implementation of '''multiclass logistic regression'''.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''import pandas as pd '''

|| These are the necessary libraries to be imported for '''Multiclass classification.'''

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Only narration

Highlight: '''iris = load_iris()'''

'''iris.data[:5]'''
|| We first load the Iris dataset using the '''load underscore iris''' method.

The dataset is stored in the variable '''iris'''.

Then we display the first five rows using the '''head''' method.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''Data Preprocessing'''
|| Now, let us prepare the data for training.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''X = iris.data '''
|| We create variable '''X''' and assign all feature columns to it.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''Y = iris.target'''
|| Next, we assign the target column to the variable '''Y'''.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''df = pd.DataFrame(X, columns=iris.feature_names)'''

'''df['target'] = Y'''
|| To analyze the data better, we create a DataFrame '''df''' using '''pd dot DataFrame'''.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''corr_matrix = df[iris.feature_names].corr()'''
|| We compute '''correlation''' values between features of the '''Iris''' dataset using '''df dot corr'''.

Now, we visualize this '''correlation''' using a '''heatmap'''.

The '''heatmap''' shows how features relate to one another.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''Train and Test Split'''
|| Next, we split the data into training and testing sets.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''Model Instantiation of Multiclass Classification and Model training'''
|| Let us now build a multiclass classification model.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''mlr = LogisticRegression(multi_class='multinomial', solver='lbfgs', max_iter=1000) '''

'''mlr.fit(X_train, Y_train)'''
|| We create an instance of '''LogisticRegression''' from the '''sklearn''' library.

Set multi underscore class equals '''multinomial '''and solver equals '''lbfgs'''.

We also set '''max underscore iter''' equals 1000 to ensure convergence.

Now we train the model using the '''fit''' method on the '''training data'''.

Ignore the warning in the output cell, if any.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''Y_train_pred = mlr.predict(X_train)'''

|| Now, we calculate and print the '''training accuracy'''.

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Hightlight '''Training Accuracy: 0.981'''
|| The '''training accuracy''' is approximately '''0.981''', which is quite good.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''Train Log Loss: 0.1308'''
|| Next, we calculate the cross-entropy loss for the training data.

A Loss of '''0.1308''' shows the model is making accurate predictions.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''plt.figure(figsize=(8, 6))'''

'''for i in range(Y_train_pred_proba.shape[1]): <nowiki># Iterate over each class</nowiki>'''

'''fpr, tpr, _ = roc_curve(Y_train == i, Y_train_pred_proba[:, i]) <nowiki># One-vs-rest for each class</nowiki>'''

'''roc_auc = auc(fpr, tpr)'''

|| Let us now plot the '''ROC curve''' and calculate the '''ROC-AUC score'''.

The '''ROC curve''' shows '''TPR vs FPR''' at various threshold values.

'''TPR''' stands for '''True Positive Rate''' that is '''recall'''.

It is the fraction of actual positives correctly identified.

'''FPR''' stands for''' False Positive Rate'''.

It is the fraction of actual negatives wrongly classified as positives.

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show output plot
|| <div style="color:#000000;">The '''ROC curve''' shows near-perfect classification.</div>

<div style="color:#000000;">The curves stay close to the '''top-left corner'''. </div>

<div style="color:#000000;">All three classes achieve an '''AUC''' of '''1.00'''. </div>

<div style="color:#000000;">This indicates the model effectively distinguishes the classes.</div>
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight: '''Predictions for Test Data'''
|| Further, we predict labels for x underscore test.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''test_data = X_test[15].reshape(1, -1)'''

'''predicted_class = mlr.predict(test_data)'''
|| We test the model on a single sample, similar to binary classification.

We compare the predicted with the actual test class.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight: '''Predicted class: 0, Actual class: 0'''
|| The predicted value is 0, which is Setosa.

The actual value is also 0, hence prediction is correct.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight '''Y_pred = mlr.predict(x_test)'''
|| '''y underscore pred '''stores predicted labels for all test samples.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight: '''print("Multiclass classification - Actual vs Predicted:")'''
|| We compare the actual class labels with the predicted labels.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight:''' Multiclass Logistic Regression - Actual vs Predicted:'''
|| The output shows both actual and predicted label arrays.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight: '''test_accuracy = accuracy_score(y_test, y_pred)'''

'''print(f"Test Accuracy: {test_accuracy:.3f}")'''
|| Now we calculate the '''test accuracy'''.

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight:''' Test Accuracy: 0.978'''
|| We get an accuracy of approximately '''0.978''', which is pretty good.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''<nowiki># Predict probabilities for test set</nowiki>'''

'''Y_test_pred_proba = mlr.predict_proba(X_test)'''

|| We also compute '''ROC-AUC score''' and '''cross-entropy loss''' for test data.

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''Test ROC-AUC Score (OvR): 0.9968'''

'''Test Log Loss: 0.1616'''

|| '''ROC-AUC score''' of '''0.9968 '''indicates excellent performance.

'''Cross-entropy loss''' of '''0.1616''' shows the predictions are accurate.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Highlight

'''conf_matrix = confusion_matrix(Y_test, Y_pred) '''

|| Let us visualize the '''confusion matrix''' of the model.

It shows how well the model classifies each class.

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show output plot
|| This matrix has three classes: 0, 1, and 2.

The '''diagonal values''' represent correct predictions.

One sample from Class 1 was incorrectly predicted as Class 2.

The absence of other misclassified values indicates that the model performs well.

A '''strong diagonal pattern''' suggests '''high classification accuracy'''.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Only narration
|| Now we have successfully classified different Iris flower classes.

This brings us to the end of the tutorial. Let us summarize.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''Summary'''
|| In this tutorial, we have learnt about* <div style="margin-left:1.27cm;margin-right:0cm;">Multiclass Classification for Logistic Regression</div>

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:

'''Assignment '''
|| As an assignment, please do the following:
* Generate the classification report of the model using '''sklearn''' method as shown.
* Use classification_report from sklearn dot metrics to display results.
* This shows '''precision''', '''recall''', '''f1-score''', and '''support''' for each class.

|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| Show slide:
|| After completing the assignment, the output should match the expected result.
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| <div style="color:#000000;">Show Slide:</div>

<div style="color:#000000;">'''FOSSEE Forum'''</div>
|| <span style="background-color:#ffffff;color:#000000;">For any general or technical questions on </span><span style="color:#000000;">'''Python for'''</span>

<span style="color:#000000;">'''Machine Learning'''</span><span style="background-color:#ffffff;color:#000000;">, visit the</span><span style="background-color:#ffffff;color:#000000;">''' FOSSEE forum'''</span><span style="background-color:#ffffff;color:#000000;"> and post your question.</span>
|- style="border:0.5pt solid #000000;padding-top:0cm;padding-bottom:0cm;padding-left:0.199cm;padding-right:0.191cm;"
|| <div style="color:#000000;">Show Slide:</div>

<div style="color:#000000;">'''Thank You'''</div>
|| <span style="color:#000000;">This is </span><span style="color:#000000;">'''Anvita Thadavoose Manjummel'''</span><span style="color:#000000;">, a FOSSEE Summer Fellow 2025, IIT Bombay signing off.</span>

<div style="color:#000000;">Thanks for joining.</div>

|-
|}

@@ Line 45: / Line 45: @@
 '''Iris flower classification'''
-|| To implement the '''Multiclass classification model '''we will,
+|| To implement the '''Multiclass classification model ''' we will,
 * Use the '''iris '''dataset to classify the '''iris '''flower.
 * To know more about the '''iris''' dataset please watch earlier tutorials.
@@ Line 51: / Line 51: @@
 |-
 || Point to the '''LR_Multiclass.ipynb'''
-|| '''LR_Multiclass dot ipynb '''is the ipython notebook file created for this demonstration.
+|| '''LR_Multiclass dot ipynb ''' is the ipython notebook file created for this demonstration.
 |-
 || Press '''Ctrl+Alt'''+'''T '''keys
@@ Line 58: / Line 58: @@
 Press '''Enter'''
 Highlight: '''(ml)'''
-|| Let us open the Linux terminal by pressing '''Ctrl, Alt''' and '''T '''keys together.
+|| Let us open the Linux terminal by pressing '''Ctrl, Alt''' and '''T ''' keys together.
 Activate the machine learning environment as shown.
@@ Line 76: / Line 76: @@
 Double Click on '''LR_Multiclass.ipynb '''file
-|| We can see the '''Jupyter Notebook''' '''Home page''' has opened in the web browser.
+|| We can see the '''Jupyter Notebook Home page''' has opened in the web browser.
 Click on the''' LR underscore Multiclass dot ipynb '''file to open it.
@@ Line 266: / Line 266: @@
 || Now we have successfully classified different Iris flower classes.
-This brings us to the end of the tutorial. Let us summarize.
+This brings us to the end of the tutorial.
 |-
 || Show slide:
 '''Summary'''
-|| In this tutorial, we have learnt about* Multiclass Classification for Logistic Regression
 |-

Python-for-Machine-Learning/C2/Logistic-Regression-MultiClass-Classification/English - Revision history

Madhurig at 07:32, 11 July 2025

Madhurig at 07:13, 11 July 2025

Nirmala Venkat: Created page with " {| border="1" |- || '''Visual Cue''' || '''Narration''' |- |- style="border:0.5pt solid #000000;padding-top:0cm;pad..."

Nirmala Venkat: Created page with "
{| border="1" |- || '''Visual Cue''' || '''Narration''' |- |- style="border:0.5pt solid #000000;padding-top:0cm;pad..."