def show_learning_curve(
est: BaseEstimator,
conf_mat_labels: List,
X_train: DataFrame,
y_train: Series,
X_test: DataFrame,
y_test: Series,
scoring_metric: str = "f1_micro",
cv: StratifiedKFold = StratifiedKFold(n_splits=12),
sizes: np.linspace = np.linspace(0.3, 1.0, 10),
fig_size: Tuple = (8, 8),
savefig: Path = Path().cwd() / "reports" / "figures" / "cm.png",
) -> None:
"""Plot the learning curve"""
fig, ax = plt.subplots(figsize=fig_size)
cm = LearningCurve(est,
cv=cv,
scoring=scoring_metric,
train_sizes=sizes,
n_jobs=-1)
cm = LearningCurve(est, classes=conf_mat_labels, ax=ax)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)
cm.finalize()
if not savefig.is_file():
fig.savefig(savefig, bbox_inches="tight", dpi=300)
def evaluation(estimator, X, Y, x, y):
classes = [Y[1], Y[0]]
f, (ax, ax1, ax2) = plt.subplots(1, 3, figsize=(18, 6))
#Confusion Matrix
cmm = ConfusionMatrix(model=estimator,
ax=ax1,
classes=classes,
label_encoder={
0.0: 'Negativo',
1.0: 'Positivo'
})
cmm.score(x, y)
#ROCAUC
viz = ROCAUC(model=estimator, ax=ax2)
viz.fit(X, Y)
viz.score(x, y)
#Learning Curve
cv_strategy = StratifiedKFold(n_splits=3)
sizes = np.linspace(0.3, 1.0, 10)
visualizer = LearningCurve(estimator,
ax=ax,
cv=cv_strategy,
scoring='roc_auc',
train_sizes=sizes,
n_jobs=4)
visualizer.fit(X, Y)
cmm.poof(), viz.poof(), visualizer.poof()
plt.show()
def learning_curve_clusterer(path="images/learning_curve_clusterer.png"):
X, y = make_blobs(n_samples=1000, centers=5)
_, ax = plt.subplots()
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(
KMeans(), ax=ax, train_sizes=sizes, scoring="adjusted_rand_score"
)
oz.fit(X, y)
oz.poof(outpath=path)
def plot_learning_curve(X, y, model, figPath=None):
"""Prints a training curve for a model (with file saving ability).
Args:
X (numpy array): Features for the evaluation.
y (numpy array): Targets for the evaluation.
model (sklearn Model): The model to visualize.
figPath (str): Where to save the figure. figPath=None does not save the figure.
"""
# create a stratified cross validation to ensure good sample
# representation.
cv = StratifiedKFold(n_splits=NUM_FOLDS, random_state=SEED, shuffle=True)
visualizer = LearningCurve(model,
cv=cv,
scoring='f1_weighted',
train_sizes=np.linspace(0.3, 1.0, 10),
n_jobs=-1)
visualizer.fit(X, y)
if figPath == None:
visualizer.show()
else:
visualizer.show(outpath=f'{figPath}/learning.png')
def learning_curve_sklearn_example(path="images/learning_curve_sklearn_example.png"):
digits = load_digits()
X, y = digits.data, digits.target
_, ax = plt.subplots(nrows=1, ncols=2, sharey=True, figsize=(9,4))
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
oz = LearningCurve(GaussianNB(), ax=ax[0], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.finalize()
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
oz = LearningCurve(SVC(gamma=0.001), ax=ax[1], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.poof(outpath=path)
def learning_curve_regressor(path="images/learning_curve_regressor.png"):
data = pd.read_csv(os.path.join(FIXTURES, "energy", "energy.csv"))
targets = ["heating load", "cooling load"]
features = [col for col in data.columns if col not in targets]
X = data[features]
y = data[targets[0]]
_, ax = plt.subplots()
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(RidgeCV(), ax=ax, train_sizes=sizes, scoring='r2')
oz.fit(X, y)
oz.poof(outpath=path)
def learning_curve_classifier(path="images/learning_curve_classifier.png"):
data = pd.read_csv(os.path.join(FIXTURES, "game", "game.csv"))
target = "outcome"
features = [col for col in data.columns if col != target]
X = pd.get_dummies(data[features])
y = data[target]
_, ax = plt.subplots()
cv = StratifiedKFold(12)
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(
MultinomialNB(), ax=ax, cv=cv, n_jobs=4,
train_sizes=sizes, scoring='f1_weighted'
)
oz.fit(X, y)
oz.poof(outpath=path)
def draw_learning_curve(self, cv, scoring='accuracy', n_jobs=5):
visualizer = LearningCurve(self.model,
cv=cv,
scoring=scoring,
n_jobs=n_jobs)
visualizer.fit(self.training_data, self.training_labels)
visualizer.poof()
def eva_model(c, n, X, y, X_test, y_test, class_names, outdir):
model = svm.LinearSVC(class_weight='balanced', dual=False, max_iter=10000, C=c)
rfe = RFE(model, n_features_to_select=n)
## learning curve
plt.clf()
viz_LC = LearningCurve(
rfe, scoring='f1_weighted', n_jobs=4
)
viz_LC.fit(X, y)
viz_LC.show(outpath=outdir + '/LC.png')
## classification report
plt.clf()
viz_CR = ClassificationReport(rfe, classes=class_names, support=True)
viz_CR.fit(X, y)
viz_CR.score(X_test, y_test)
viz_CR.show(outpath=outdir + '/CR.png')
## confusion matrix
plt.clf()
viz_CM = ConfusionMatrix(rfe, classes=class_names)
viz_CM.fit(X, y)
viz_CM.score(X_test, y_test)
viz_CM.show(outpath=outdir + '/CM.png')
## precision recall curve
plt.clf()
viz_PRC = PrecisionRecallCurve(rfe, per_class=True, iso_f1_curves=True,
fill_area=False, micro=False, classes=class_names)
viz_PRC.fit(X, y)
viz_PRC.score(X_test, y_test)
viz_PRC.show(outpath=outdir + '/PRC.png',size=(1080,720))
## class prediction error
plt.clf()
viz_CPE = ClassPredictionError(
rfe, classes=class_names
)
viz_CPE.fit(X, y)
viz_CPE.score(X_test, y_test)
viz_CPE.show(outpath=outdir + '/CPE.png')
## ROCAUC
plt.clf()
viz_RA = ROCAUC(rfe, classes=class_names, size=(1080,720))
viz_RA.fit(X, y)
viz_RA.score(X, y)
viz_RA.show(outpath=outdir + '/RA.png')
fit = rfe.fit(X,y)
y_predict = fit.predict(X_test)
f1 = f1_score(y_test, y_predict, average='weighted')
features_retained_RFE = X.columns[rfe.get_support()].values
feature_df =pd.DataFrame(features_retained_RFE.tolist())
feature_df.to_csv(outdir + '/features.csv', sep='\t', index=False)
return f1
def generate_learning_curve(model, clf_name, scoring, sizes, cv, n_jobs,
dataset_name, X_train, y_train):
viz = LearningCurve(model,
cv=cv,
scoring=scoring,
train_sizes=sizes,
n_jobs=n_jobs)
viz.fit(X_train, y_train)
viz.show("results/{}_learning_curve_{}.png".format(clf_name, dataset_name))
plt.clf()
def run_crossvalidation(model,
x_train,
y_train,
cv=5,
scoring="accuracy",
report=None,
model_name=None):
"""
Runs cross validation on a certain model.
Parameters
----------
model : Model
Model to cross validate
x_train : nd-array
Training data
y_train : nd-array
Testing data
cv : int, Crossvalidation Generator, optional
Cross validation method, by default 5
scoring : str, optional
Scoring method, by default 'accuracy'
"""
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(15, 5))
visualizer_scores = CVScores(model, cv=cv, scoring=scoring, ax=axes[0])
visualizer_scores.fit(x_train, y_train)
visualizer_scores.finalize()
visualizer_lcurve = LearningCurve(model,
cv=cv,
scoring=scoring,
ax=axes[1])
visualizer_lcurve.fit(x_train, y_train)
visualizer_lcurve.finalize()
visualizer_scores.show()
visualizer_lcurve.show()
if report or _global_config['track_experiments']: # pragma: no cover
fig.savefig(os.path.join(IMAGE_DIR, model_name, "cv.png"))
def visualizeLearningCurve(classifier, features, labels, scoring='precision'):
sizes = numpy.linspace(0.1, 1.0, 10)
cv = StratifiedKFold(10)
visualizer = LearningCurve(classifier,
cv=cv,
train_sizes=sizes,
scoring=scoring,
n_jobs=10)
visualizer.fit(features.drop(["appid", "name"], axis=1),
list(map(convertLabelToNumber, labels)))
visualizer.poof()
def learning_curve_clusterer(path="images/learning_curve_clusterer.png"):
X, y = make_blobs(n_samples=1000, centers=5)
_, ax = plt.subplots()
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(KMeans(),
ax=ax,
train_sizes=sizes,
scoring="adjusted_rand_score")
oz.fit(X, y)
oz.poof(outpath=path)
def learning_curve_regressor(path="images/learning_curve_regressor.png"):
data = pd.read_csv(os.path.join(FIXTURES, "energy", "energy.csv"))
targets = ["heating load", "cooling load"]
features = [col for col in data.columns if col not in targets]
X = data[features]
y = data[targets[0]]
_, ax = plt.subplots()
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(RidgeCV(), ax=ax, train_sizes=sizes, scoring='r2')
oz.fit(X, y)
oz.poof(outpath=path)
def run_crossvalidation(model,
x_train,
y_train,
cv=5,
scoring="accuracy",
learning_curve=False):
"""
Runs cross validation on a certain model.
Parameters
----------
model : Model
Model to cross validate
x_train : nd-array
Training data
y_train : nd-array
Testing data
cv : int, Crossvalidation Generator, optional
Cross validation method, by default 5
scoring : str, optional
Scoring method, by default 'accuracy'
learning_curve : bool, optional
If true plot learning curve, by default False
Returns
-------
list
List of cross validation curves
"""
# TODO: Make curves slightly bigger
visualizer_scores = CVScores(model, cv=cv, scoring=scoring)
visualizer_scores.fit(x_train, y_train)
visualizer_scores.show()
if learning_curve:
visualizer_lcurve = LearningCurve(model, cv=cv, scoring=scoring)
visualizer_lcurve.fit(x_train, y_train)
visualizer_lcurve.show()
return visualizer_scores.cv_scores_
def yellow_brick_learning_curve(model, x, y, cpu_count, cv_count,
scoring_metric):
"""
"""
# Create the learning curve visualizer
cv = StratifiedKFold(n_splits=cv_count)
sizes = np.linspace(0.3, 1.0, 10)
# Instantiate the classification model and visualizer
visualizer = LearningCurve(model,
cv=cv,
scoring=scoring_metric,
train_sizes=sizes,
n_jobs=cpu_count)
visualizer.fit(x, y) # Fit the data to the visualizer
visualizer.show() # Finalize and render the figure
def hyperparameter_tuning(fname="hyperparameter_tuning.png"):
# Create side-by-side axes grid
_, axes = plt.subplots(ncols=2, figsize=(18, 6))
# Load the concrete dataset
data = load_concrete(split=False)
# Create a list of alphas to cross-validate against
alphas = np.logspace(-10, 1, 400)
# Add AlphaSelection to the left
oz = AlphaSelection(LassoCV(alphas=alphas), ax=axes[0])
oz.fit(data.X, data.y)
oz.finalize()
# Add LearningCurve to the right
oz = LearningCurve(RandomForestRegressor(), scoring='r2', ax=axes[1])
oz.fit(data.X, data.y)
oz.finalize()
# Save figure
path = os.path.join(FIGURES, fname)
plt.tight_layout()
plt.savefig(path)
def learning_curves(models, X, y):
"""
:params models: Modelos a serem avaliados
:params X: Dados de Treino variaveis independentes
:params y: Dados de Treino variavel dependente
:return: Viz da curvas de apendizagem
"""
cv_strategy = StratifiedKFold(n_splits=3)
for model in models:
sizes = np.linspace(0.3, 1.0, 10)
viz = LearningCurve(model,
cv=cv_strategy,
scoring='roc_auc',
train_sizes=sizes,
n_jobs=4)
viz.fit(X, y)
viz.show()
def learning_curve(model, X, y):
# from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import RepeatedStratifiedKFold
from yellowbrick.model_selection import LearningCurve
# Create the learning curve visualizer
# cv = StratifiedKFold(12)
cv = RepeatedStratifiedKFold(n_splits=5, n_repeats=10, random_state=1)
sizes = np.linspace(0.3, 1.0, 10)
viz = LearningCurve(model,
cv=cv,
train_sizes=sizes,
scoring='neg_log_loss',
n_jobs=4)
# Fit and poof the visualizer
viz.fit(X, y)
viz.poof()
def learning_curve_classifier(path="images/learning_curve_classifier.png"):
data = pd.read_csv(os.path.join(FIXTURES, "game", "game.csv"))
target = "outcome"
features = [col for col in data.columns if col != target]
X = pd.get_dummies(data[features])
y = data[target]
_, ax = plt.subplots()
cv = StratifiedKFold(12)
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(MultinomialNB(),
ax=ax,
cv=cv,
n_jobs=4,
train_sizes=sizes,
scoring='f1_weighted')
oz.fit(X, y)
oz.poof(outpath=path)
residuals_plot(model, x_test, preds, hist=False, ax=ax[index])
prediction_error(model, x_test, preds, ax=ax)
# Do some scoring on XGB estimators
# Validation curve
viz = ValidationCurve(XGBRegressor(objective="reg:squarederror"),
param_name="max_depth",
param_range=np.arange(1, 11),
cv=5,
scoring="r2")
viz.fit(x_train, y_train)
viz.show()
# Learning curve
model = XGBRegressor(objective="reg:squarederror")
viz_2 = LearningCurve(model, scoring="r2")
viz_2.fit(x_train, y_train)
viz_2.show()
model = RFECV(LassoCV(), cv=5, scoring='r2')
model.fit(x_train, y_train)
model.show()
"""
Section: 5
Time-Series Algorithms
"""
# Fitting ARIMA
# Original Series
# plt.rcParams.update({'figure.figsize':(9,7), 'figure.dpi':120})
fig, axes = plt.subplots(3, 1, sharex=True)
plot_acf(main_data.traffic_volume, ax=axes[0])
def learning():
X, y = load_energy()
sizes = np.linspace(0.3, 1.0, 10)
oz = LearningCurve(RidgeCV(), train_sizes=sizes, scoring="r2", ax=newfig())
oz.fit(X, y)
savefig(oz, "learning_curve")
from yellowbrick.classifier.rocauc import roc_auc
roc_auc(tree1, X_train, y_train, X_test=X_test, y_test=y_test, classes=["Low_damage","Medium_damage","High_damage"])
#class weight balanced didn't improve it!
from sklearn.model_selection import permutation_test_score
score, permutation_scores, pvalue = permutation_test_score(
tree1, X_train, y_train, scoring="accuracy", cv=5, n_permutations=20, n_jobs=1)
print("Classification score %s (pvalue : %s)" % (score, pvalue))
scoring = make_scorer(f1_score, average = 'micro')
from yellowbrick.model_selection import LearningCurve
visualizer = LearningCurve(
tree1, cv=10, scoring=scoring,verbose = 0
)
visualizer.fit(X_train, y_train) # Fit the data to the visualizer
visualizer.show()
"""# > **Random Forest**"""
from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier(oob_score = True,n_estimators=250)
clf.get_params
clf.fit(X_train,y_train)
y_clf = clf.predict(X_test)
# ### Task 10: Learning Curves # In[38]: from yellowbrick.model_selection import LearningCurve from sklearn.linear_model import LassoCV from pylab import rcParams rcParams['figure.figsize'] = 15, 10 # Create the learning curve visualizer sizes = np.linspace(0.3, 1.0, 10) # Create the learning curve visualizer, fit and poof viz = LearningCurve(LassoCV(), train_sizes=sizes, scoring='r2') viz.fit(X, y) viz.poof() # # ### Task 11: Hyperparamter Tuning # The `AlphaSelection` Visualizer demonstrates how different values of alpha influence model selection during the regularization of linear models. # In[16]: from sklearn.linear_model import LassoCV
print(classification_report(y_test, y_test_pred))
# In[42]:
#Training and Testing error with new data
print(classification_report(y_train_New, y_train_pred_New))
print(classification_report(y_test_New, y_test_pred_New))
# In[44]:
#Learning Curve
from sklearn.model_selection import cross_validate
from yellowbrick.model_selection import LearningCurve
from sklearn.model_selection import StratifiedKFold
cv = StratifiedKFold(n_splits=12)
sizes = np.linspace(0.3, 1.0, 10)
model = ExtraTreesRegressor(n_estimators=250,
random_state=0,
max_depth=80,
max_features='auto')
visualizer = LearningCurve(model,
cv=cv,
scoring='roc_auc',
train_sizes=sizes,
n_jobs=5)
visualizer.fit(X_train_New, y_train_New) # Fit the data to the visualizer
visualizer.show() # Finalize and render the figure
result2 = cross_val_score(arbre, x_train, y_train, cv=kplis_strat)
print(' score kplis strat cross validation :{}'.format(result2))
print('moyenne score cross validation : {:.2f}'.format(result2.mean()))
result3 = cross_val_score(arbre, x_train, y_train, cv=shuffle)
print(' score shuffle split cross validation :{}'.format(result3))
print('moyenne score cross validation : {:.2f}'.format(result3.mean()))
cm = ConfusionMatrix(arbre, classes=[0, 1, 2, 3, 4, 5, 6], percent=True)
cm.fit(x_train, y_train)
cm.score(x_test, y_test)
cm.poof()
size = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]
lc = LearningCurve(DecisionTreeClassifier(), train_sizes=size, score='r2')
lc.fit(x_train, y_train)
lc.poof()
''' ---------------------- Forêt aléatoire ------------------------'''
foret = RandomForestClassifier(n_estimators=120,
max_features='sqrt',
n_jobs=-1,
random_state=0)
foret.fit(x_train, y_train)
result = cross_val_score(foret, x_train, y_train, cv=5)
print(' score cross validation :{}'.format(result))
print('moyenne score cross validation : {:.2f}'.format(result.mean()))
result1 = cross_val_score(foret, x_train, y_train, cv=kplis)
def learning_curve_sklearn_example(
path="images/learning_curve_sklearn_example.png"):
digits = load_digits()
X, y = digits.data, digits.target
_, ax = plt.subplots(nrows=1, ncols=2, sharey=True, figsize=(9, 4))
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
oz = LearningCurve(GaussianNB(), ax=ax[0], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.finalize()
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
oz = LearningCurve(SVC(gamma=0.001), ax=ax[1], cv=cv, n_jobs=4)
oz.fit(X, y)
oz.poof(outpath=path)
visualizer = ClassificationReport(model)
visualizer.score(X_test, y_test)
visualizer.show()
# 混淆矩阵
visualizer = ConfusionMatrix(model)
visualizer.score(X_test, y_test)
visualizer.show()
# 阈值选择
visualizer = DiscriminationThreshold(model)
visualizer.fit(X_train, y_train)
visualizer.show()
# 学习率
visualizer = LearningCurve(model, scoring='f1_weighted')
visualizer.fit(X_train, y_train)
visualizer.show()
# 交叉验证
visualizer = CVScores(model, cv=5, scoring='f1_weighted')
visualizer.fit(X_train, y_train)
visualizer.show()
# 特征重要性
visualizer = FeatureImportances(model)
visualizer.fit(X_train, y_train)
visualizer.show()
# 特征递归消减
visualizer = RFECV(model, cv=5, scoring='f1_weighted')
case_name = "mg_sizing_dataset_with_loc"
df = pd.read_csv("results/" + case_name + ".csv", sep=";|,", engine="python", index_col='index')
#df = df.loc[df['off-grid'] == 1]
X = df[features]
scaler.fit(X)
X = scaler.transform(X)
# X = pd.DataFrame(scaler.transform(X), index=X.index, columns=X.columns)
targets = ["PV","BAT","RBAT","INV","GEN","NPV"]
y = df[targets]
cv = StratifiedKFold(12)
param_range = np.arange(1, 30, 1)
cv = KFold(n_splits=12, random_state=40, shuffle=True)
viz = ValidationCurve(
KNeighborsRegressor(), param_name="n_neighbors", param_range=param_range, scoring="r2", cv=cv, n_jobs=8
)
viz.fit(X, y)
viz.show()
visualizer = LearningCurve(KNeighborsRegressor(), scoring='r2', random_state=2, cv=cv, shuffle=True)
visualizer.fit(X, y)
visualizer.show()
vis = CVScores(KNeighborsRegressor(), cv=cv, scoring='r2')
vis.fit(X, y) # Fit the data to the visualizer
vis.show()
param_name='n_neighbors',
param_range=n_neighbors,
cv=5,
scoring=rmse_score,
# n_jobs=-1,
ax=ax)
val_curve.fit(X, y)
val_curve.poof()
fig.tight_layout()
plt.show()
fig, ax = plt.subplots(figsize=(16, 9))
l_curve = LearningCurve(
KNeighborsRegressor(n_neighbors=best_k),
train_sizes=np.arange(.1, 1.01, .1),
scoring=rmse_score,
cv=5,
# n_jobs=-1,
ax=ax)
l_curve.fit(X, y)
l_curve.poof()
fig.tight_layout()
plt.show()
# Binary Classification
y_binary = (y > y.median()).astype(int)
n_neighbors = tuple(range(5, 151, 10))
n_folds = 5
scoring = 'roc_auc'
pipe = Pipeline([('scaler', StandardScaler()),
viz.fit(x_data,y_data)
viz.show()
# %%
best_params = dt.hyperParameterTuning(x_train,y_train)
print(best_params)
dt_tuned = DecisionTreeClassifier(max_depth=best_params['max_depth'], min_samples_leaf=best_params['min_samples_leaf'], random_state=rs)
# %%
sizes = np.linspace(0.3, 1.0, 10)
# Instantiate the classification model and visualizer
visualizer = LearningCurve(
dt_tuned, scoring='f1_weighted', train_sizes=sizes, n_jobs=4
)
visualizer.fit(x_data,y_data) # Fit the data to the visualizer
visualizer.show()
# %% [markdown]
# # 3. Support Vector Machine
# %%
class SupportVectorMachine():
def trainTest(self,x_train,x_test, y_train, y_test):
scaler = StandardScaler()
scaled_x_train = scaler.fit_transform(x_train)
scaled_x_test = scaler.fit_transform(x_test)
cs = [x/10000 for x in [1, 10, 100, 1000, 10000, 100000, 1000000]]
def upper_region_classifier():
ur_dataset = pd.read_csv("../resources/datasets/ur_dataset.csv",
na_values='?',
dtype='category')
print("UR classes", ur_dataset.groupby(SECOND_LEVEL_TARGET).size())
# Separate training feature & training labels
X = ur_dataset.drop(['class'], axis=1)
y = ur_dataset['class']
# Spot check
# spot_check_algorithms(X, y)
# pipeline = Pipeline([
# ('bow', CountVectorizer()),
# ('classifier', BernoulliNB()),
# ])
# Create a cross-validation strategy
# StratifiedKFold cross-validation strategy to ensure all of our classes in each split are represented with the same proportion.
cv = RepeatedStratifiedKFold(n_splits=3, random_state=42)
# https://machinelearningmastery.com/automate-machine-learning-workflows-pipelines-python-scikit-learn/
# create feature union
features = []
# features.append(('pca', MCA(n_components=3)))
features.append(('select_best', SelectKBest(k=15)))
feature_union = FeatureUnion(features)
# create pipeline
estimators = []
estimators.append(('feature_union', feature_union))
estimators.append(('ROS', RandomOverSampler(random_state=42)))
estimators.append(('logistic', RandomForestClassifier(random_state=13)))
model = Pipeline(estimators)
imba_pipeline = make_pipeline(RandomOverSampler(random_state=42),
SelectKBest(k=15),
RandomForestClassifier(random_state=13))
scores = cross_val_score(imba_pipeline,
X,
y,
scoring='f1_micro',
cv=cv,
n_jobs=-1)
print("After oversampling mean", scores.mean())
############################################# Hyper-parameter Tuning ###########################################
params = {
'n_estimators': [5, 10, 20, 30],
'max_depth': [4, 6, 10, 12],
'random_state': [13]
}
new_params = {
'randomforestclassifier__' + key: params[key]
for key in params
}
grid_imba = GridSearchCV(imba_pipeline,
param_grid=new_params,
cv=cv,
scoring='f1_micro',
return_train_score=True)
grid_imba.fit(X, y)
print(grid_imba.best_params_)
print(grid_imba.best_score_)
#refer - https://stackoverflow.com/questions/40057049/using-confusion-matrix-as-scoring-metric-in-cross-validation-in-scikit-learn
model = grid_imba.best_estimator_
sizes = np.linspace(0.3, 1.0, 10)
# Instantiate the classification model and visualizer
visualizer = LearningCurve(model,
cv=cv,
scoring='f1_micro',
train_sizes=sizes,
n_jobs=4)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.show() # Finalize and render the figure
