Leer Challenge: Classifying Inseparable Data

You will use the following dataset with two features:


              1234
            
import pandas as pd

df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b71ff7ac-3932-41d2-a4d8-060e24b00129/circles.csv')
print(df.head())

If you run the code below and take a look at the resulting scatter plot, you'll see that the dataset is not linearly separable:


              123456
            
import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b71ff7ac-3932-41d2-a4d8-060e24b00129/circles.csv')
plt.scatter(df['X1'], df['X2'], c=df['y'])
plt.show()

Let's use cross-validation to evaluate a simple logistic regression on this data:


              123456789101112131415161718
            
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score

df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b71ff7ac-3932-41d2-a4d8-060e24b00129/circles.csv')
X = df[['X1', 'X2']]
y = df['y']

X = StandardScaler().fit_transform(X)
lr = LogisticRegression().fit(X, y)

y_pred = lr.predict(X)
plt.scatter(df['X1'], df['X2'], c=y_pred)
plt.show()

print(f'Cross-validation accuracy: {cross_val_score(lr, X, y).mean():.2f}')

As you can see, regular Logistic Regression is not suited for this task. Using polynomial regression may help improve the model's performance. Additionally, employing GridSearchCV allows you to find the optimal C parameter for better accuracy.

This task also uses the Pipeline class. You can think of it as a sequence of preprocessing steps. Its .fit_transform() method sequentially applies .fit_transform() to each step in the pipeline.

Taak

Swipe to start coding

You are given a dataset described as a DataFrame in the df variable.

Create a pipeline that will hold the polynomial features of degree 2 of X and be scaled and store the resulting pipeline in the pipe variable.
Create a param_grid dictionary to with values [0.01, 0.1, 1, 10, 100] of the C hyperparameter.
Initialize and train a GridSearchCV object and store the trained object in the grid_cv variable.

Oplossing

Was alles duidelijk?

Bedankt voor je feedback!

Sectie 1. Hoofdstuk 13

single

Vraag AI

Vraag wat u wilt of probeer een van de voorgestelde vragen om onze chat te starten.

Veeg om het menu te tonen