In python. We are using the Iris dataset

Question

Now, it's your turn to make a Logistic Regression model, an ROC curve, and calculate some basic metrics.

IMPORTANT: This time, do all model training with all four predictors, and instead of predicting if the species is or is not Iris Setosa, predict whether a species is or is not Iris Versicolor.

In the following cell, build your training/testing data (based off of the original split into train/test data), fit the logistic model, and make a confusion matrix.

Finally, report, using predictions on the testing data:

1. The model accuracy as the variable acc
2. Sensitivity as TPR
3. Specifity as TNR

Answer 1

This is outline of the steps for this popular ML problem:

1. Import the necessary libraries:

import pandas as pd

import numpy as np

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression

from sklearn.metrics import confusion_matrix

from sklearn.metrics import roc_curve

2. Load the Iris dataset:

data = pd.read_csv('iris.csv')

3. Create the training and testing datasets:

X = data.drop(['species'], axis=1)

y = data['species']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

4. Create a Logistic Regression model and fit it to the training data:

model = LogisticRegression()

model.fit(X_train, y_train)

5. Make predictions on the testing data:

y_pred = model.predict(X_test)

6. Create a confusion matrix:

cm = confusion_matrix(y_test, y_pred)

7. Calculate the model accuracy, sensitivity, and specificity:

acc = (cm[0][0] + cm[1][1]) / (cm[0][0] + cm[1][1] + cm[0][1] + cm[1][0])

TPR = cm[1][1] / (cm[1][1] + cm[1][0])

TNR = cm[0][0] / (cm[0][0] + cm[0][1])

8. Create an ROC curve:

fpr, tpr, thresholds = roc_curve(y_test, y_pred)

Please contact me if you need help to understand topics in data science, machine learning, algorithms, data structures