def prediction_error_plot(lin_model,x_train, y_train, x_test, y_test):
fig = plt.figure(figsize=(16,12))
ax1 = fig.add_subplot(111)
visualizer_pred_err = PredictionError(lin_model, ax=ax1)
visualizer_pred_err.fit(x_train, y_train) # Fit the training data to the visualizer
visualizer_pred_err.score(x_test, y_test) # Evaluate the model on the test data
visualizer_pred_err.show()
def prediction_error_plot(self) -> None:
"""Plot the actual targets from the dataset against the predicted values
generated by our model. This allows us to see how much variance is in the model.
"""
visualizer = PredictionError(self.trained_model)
visualizer.fit(self.X_train,
self.y_train) # Fit the training data to the visualizer
visualizer.score(self.X_test,
self.y_test) # Evaluate the model on the test data
save_dir = f"{self.plots_dir}/prediction_error_plot_{self.model_id}.png"
visualizer.show(outpath=save_dir)
if not LOCAL:
upload_to_s3(save_dir,
f'plots/prediction_error_plot_{self.model_id}.png',
bucket=S3_BUCKET_NAME)
plt.clf()
def lasso_regression(X_train, y_train, X_test, y_test, plot):
"""
Perfomring a lasso regression with built in CV and plotting the feature importance
"""
# Fit the ridge regression
reg = LassoCV()
reg.fit(X_train, y_train)
print("Best alpha using built-in LassoCV: %f" % reg.alpha_)
print("Best score using built-in LassoCV: %f" % reg.score(X_train, y_train))
coef = pd.Series(reg.coef_, index=X_train.columns)
print(
"Lasso picked "
+ str(sum(coef != 0))
+ " variables and eliminated the other "
+ str(sum(coef == 0))
+ " variables"
)
# Extract the feature importance
imp_coef = coef.sort_values()
# Plot the feature importance
if plot:
plt.rcParams["figure.figsize"] = (8.0, 10.0)
imp_coef.plot(kind="barh")
plt.title("Feature importance using Lasso Model")
plt.show()
# Plotting the prediction error
visualizer = PredictionError(reg, size=(1080, 720))
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_test, y_test) # Evaluate the model on the test data
visualizer.show() # Finalize and render the figure
# Visualizing the regression
visualizer = ResidualsPlot(reg, size=(1080, 720))
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_test, y_test) # Evaluate the model on the test data
visualizer.show() # Finalize and render the figure
# Using the test data to calculate a score
y_pred = reg.predict(X_test)
# Return metrics
return {
"name": "Lasso Regression",
"R squared": reg.score(X_test, y_test),
"RMSE": rmse(y_test, y_pred),
"R squared training": reg.score(X_train, y_train),
"MAE": mean_absolute_error(y_test, y_pred),
}
lm5 = LinearRegression().fit(x_train,y_train)
lm5_pred=lm5.predict(x_test)
print("RMSE = ", np.sqrt(mean_squared_error(y_test,lm5_pred)))
print("R^2 = ", r2_score(y_test,lm5_pred))
# In[30]:
from yellowbrick.regressor import PredictionError, ResidualsPlot
visualizer=PredictionError(lm5).fit(x_train, y_train)
visualizer.score(x_test, y_test)
visualizer.show()
# In[32]:
#TASK 7: INTERACTION EFFECT - SYNERGY
advert['interaction']= advert['TV'] * advert['radio']
x=advert[['TV', 'radio', 'interaction']]
y=advert.sales
x_train, x_test, y_train, y_test= train_test_split(x,y, random_state=1)
lm6 = LinearRegression().fit(x_train,y_train)
def scikit_learn_method(x,
y,
min_x,
max_x,
max_y,
ln_bool,
df=all_scopus,
test_size=0.2,
random_state=0):
# https://stackoverflow.com/questions/42988348/typeerror-cannot-convert-the-series-to-class-float
if ln_bool:
y = np.log(y)
# set random_state = 0 for consistent seed
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=0)
# reshape (-1, 1) - gives us 1 sample; no need to reshape y
# https://datatofish.com/dropna/
# https://stackoverflow.com/questions/18691084/what-does-1-mean-in-numpy-reshape
# https://stackoverflow.com/questions/53723928/attributeerror-series-object-has-no-attribute-reshape
# https://stackoverflow.com/questions/35082140/preprocessing-in-scikit-learn-single-sample-depreciation-warning
x_train = x_train.values.reshape(-1, 1)
x_test = x_test.values.reshape(-1, 1)
model_withOutliers = LinearRegression()
model_withOutliers = model_withOutliers.fit(x_train, y_train)
print('y-hat = %sx + %s' %
(model_withOutliers.coef_[0], model_withOutliers.intercept_))
# https://stackoverflow.com/questions/41635448/how-can-i-draw-scatter-trend-line-on-matplot-python-pandas/41635626
from sklearn.metrics import r2_score
plt.scatter(x, y) # with outliers
plt.title('With outliers')
m, b = model_withOutliers.coef_[0], model_withOutliers.intercept_
plt.plot(x, m * x + b)
plt.show()
text = f"$y={m:0.3f}\;x{b:+0.3f}$\n$R^2 = {r2_score(y, m * x + b):0.3f}$"
plt.gca().text(0.05,
0.95,
text,
transform=plt.gca().transAxes,
fontsize=14,
verticalalignment='bottom')
# https://www.scikit-yb.org/en/latest/api/regressor/peplot.html
from sklearn.linear_model import Lasso
from yellowbrick.regressor import PredictionError
lasso_model = Lasso()
visualizer = PredictionError(lasso_model)
visualizer.fit(x_train, y_train) # Fit the training data to the visualizer
visualizer.score(x_test, y_test) # Evaluate the model on the test data
visualizer.show()
# https://stackoverflow.com/questions/28876243/how-to-delete-the-current-row-in-pandas-dataframe-during-df-iterrows
plt.xlim(min_x, max_x) # without outliers
plt.ylim(0, max_y)
plt.title('Without outliers')
plt.scatter(x, y)
plt.show()
text = f"$y={m:0.3f}\;x{b:+0.3f}$\n$R^2 = {r2_score(y, m*x+b):0.3f}$"
plt.gca().text(0.05,
0.95,
text,
transform=plt.gca().transAxes,
fontsize=14,
verticalalignment='bottom')
y_pred_with_outliers = model_withOutliers.predict(x_test)
sum_outliers = 0
for i in range(len(df)):
squared_with_outliers = (y_test - y_pred_with_outliers)**2
sum_outliers += squared_with_outliers
mean = sum_outliers / len(df)
rms = mean**0.5
rms_value = 0
for element in rms:
rms_value += element
rms_value = rms_value / len(rms)
print('Root mean squared, with outliers:', rms_value)
imr = SimpleImputer(strategy='median')
X = imr.fit_transform(X)
# Create the train and test data
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42
)
# Instantiate the linear model and visualizer
model = Lasso()
visualizer = PredictionError(model, size=(1080, 720))
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_test, y_test) # Evaluate the model on the test data
visualizer.show() # Draw the data
# In[88]:
from sklearn.linear_model import LinearRegression
regr_linear = LinearRegression()
# Load regression dataset
#Index(['confirmed', 'deaths', 'recovered',
# 'active', 'incident_rate', 'people_tested', 'people_hospitlized', 'mortality_rate', 'testing_rate', 'hospitalization_rate'],
#dtype='object')
def prediction_error_plot(self):
visualizer = PredictionError(self.pipe)
visualizer.score(self.X_test, self.y_test)
return visualizer.show()