def setup_mummify():
subprocess.run("echo 'test_mummify.py' >> .gitignore", shell=True)
subprocess.run("echo '__pycache__' >> .gitignore", shell=True)
contents = """import mummify
accuracy = 0.80
mummify.log(f'Accuracy: {accuracy}')
"""
with open("model.py", "w") as f:
f.write(contents)
subprocess.run("python model.py", shell=True)
import dill
import mummify
n_samples = 1000
n_outliers = 50
X, y, coef = make_regression(n_samples=n_samples,
n_features=1,
n_informative=1,
noise=10,
coef=True,
random_state=0)
np.random.seed(0)
X[:n_outliers] = 3 + 0.5 * np.random.normal(size=(n_outliers, 1))
y[:n_outliers] = -3 + 10 * np.random.normal(size=n_outliers)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=42)
model = LinearRegression()
model.fit(X_train, y_train)
model.score(X_test, y_test)
with open('exercises/regression.pkl', 'wb') as f:
dill.dump(model, f)
mummify.log('')
from sklearn.datasets import load_wine
from sklearn.neighbors import KNeighborsClassifier
import mummify
data = load_wine()
X, y = data.data, data.target
model = KNeighborsClassifier(n_neighbors=4)
model.fit(X, y)
accuracy = round(model.score(X, y), 4)
mummify.log(f'Accuracy: {accuracy}')
lambda x: pd.to_numeric(str(x).split(' ')[0], errors='coerce')
)
df['total_stops'] = df['total_stops'].fillna(0)
df = df.rename(columns={
'date_of_journey': 'date',
'total_stops': 'stops',
'source': 'origin'
})
y = df['price']
X = df[['date', 'origin', 'destination', 'stops']]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
mapper = DataFrameMapper([
('date', DateEncoder(), {'input_df': True}),
('origin', LabelBinarizer()),
('destination', LabelBinarizer()),
('stops', None)
], df_out=True)
model = LinearRegression()
pipe = make_pipeline(mapper, model)
pipe.fit(X_train, y_train)
score = pipe.score(X_test, y_test)
with open('pipe.pkl', 'wb') as f:
pickle.dump(pipe, f)
mummify.log(f'R2 Score: {round(score, 4)}')
X = df.drop(target, axis=1)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.25,
random_state=42)
mapper = DataFrameMapper(
[
("hexcode", HexTransformer(), {
"input_df": True
}),
(["diameter"], StandardScaler()),
(["weight"], StandardScaler()),
],
df_out=True,
)
Z_train = mapper.fit_transform(X_train)
Z_test = mapper.transform(X_test)
model = KNeighborsClassifier(n_neighbors=4)
pipe = make_pipeline(mapper, model)
pipe.fit(X_train, y_train)
score = pipe.score(X_test, y_test)
with open("pipe.pkl", "wb") as f:
pickle.dump(pipe, f)
mummify.log(f"Accuracy: {round(score, 4)}")