ML project structure in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a folder for storing raw data in an ML project.

ML Python

import os
os.makedirs('data/[1]', exist_ok=True)

Drag options to blanks, or click blank then click option'

Araw

Bmodels

Cscripts

Dresults

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing 'models' or 'scripts' folders instead of 'raw' for data storage.

The 'raw' folder is typically used to store the original unprocessed data in an ML project.

2fill in blank

medium

Complete the code to load a dataset CSV file from the data folder.

ML Python

import pandas as pd
df = pd.read_csv('data/[1]/dataset.csv')

Drag options to blanks, or click blank then click option'

Amodels

Braw

Cnotebooks

Dscripts

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'models' or 'scripts' folder which do not contain raw data.

The dataset CSV file is usually stored in the 'raw' data folder before processing.

3fill in blank

hard

Fix the error in the code to save a trained model to the models folder.

ML Python

import joblib
joblib.dump(model, 'models/[1].pkl')

Drag options to blanks, or click blank then click option'

Ascript

Bdataset

Ctrained_model

Ddata

Attempts:

3 left

💡 Hint

Common Mistakes

Saving the model with wrong or confusing file names.

The trained model should be saved with a descriptive name like 'trained_model' in the models folder.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps filenames to their sizes in the data/raw folder.

ML Python

import os
file_sizes = {f: os.path.getsize(os.path.join('data/raw', [1])) for [2] in os.listdir('data/raw')}

Drag options to blanks, or click blank then click option'

Af

Bfilename

C'filename'

Dfile

Attempts:

3 left

💡 Hint

Common Mistakes

Using string literals instead of variable names in path join.

Use the variable name 'filename' consistently to refer to each file in the folder.

5fill in blank

hard

Fill all three blanks to create a function that loads data, trains a model, and saves it.

ML Python

def train_and_save(data_path, model_path):
    import pandas as pd
    from sklearn.linear_model import LogisticRegression
    df = pd.read_csv(data_path)
    X = df.drop('[1]', axis=1)
    y = df['[2]']
    model = LogisticRegression()
    model.fit(X, y)
    import joblib
    joblib.dump(model, model_path + '/[3].pkl')

Drag options to blanks, or click blank then click option'

Atarget

Blabel

Ctrained_model

Ddata

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong column names or file names that don't match conventions.

The target column is often named 'label'. The saved model file is named 'trained_model'.