def fit(self):
"""
Performs the search
"""
self.train, self.test = train_test_split(self.dataset, test_size=0.1)
self.X_train = self.train.drop(columns=self.target)
self.y_train = self.train[self.target]
self.X_test = self.test.drop(columns=self.target)
self.y_test = self.test[self.target]
if self.problem_type == "classification":
from pycaret.classification import automl, compare_models, setup
else:
from pycaret.regression import automl, compare_models, setup
experiment = setup(data=self.train, target=self.target, silent=True, html=False)
compare_models(**self.automl_settings)
self.automl_pipeline = automl()
if __name__ == "__main__":
df = load_combine_saif_liu_data()
sample = False
if sample:
df = df.groupby(
'emotion',
group_keys=False).apply(lambda x: x.sample(min(len(x), 100)))
vector_df_filepath = 'data/vector_df.csv'
if os.path.exists(vector_df_filepath):
vector_df = pd.read_csv(vector_df_filepath)
else:
vectors = df['tweet'].swifter.apply(get_text_vector)
vector_df = pd.DataFrame(
vectors.array,
columns=[f'v{r}' for r in range(vectors.iloc[0].shape[0])])
vector_df.to_csv(vector_df_filepath)
data_df = pd.concat(
[vector_df,
pd.DataFrame(df['emotion']).reset_index(drop=True)],
axis=1)
models = pycc.setup(data=data_df, target='emotion', session_id=123)
best = pycc.compare_models()
pycc.save_model(best, 'lr_emotion.model')
with open('pycc_setup.pk', 'wb') as f:
pk.dump(models, f)
"""#### No missing values
## Visualization
"""
plt.figure(figsize=(12,12))
plt.pie(data['Type'].value_counts(), labels=data['Type'].value_counts().index)
plt.title('Class Distribution')
plt.show()
"""## Setup, it is like pipeline where we can pass peprocessing and transformation steps."""
setup(
data = data,
target = 'Type', #target meaning the target feature
normalize = True,
train_size = 0.7
)
models()
best_model = compare_models()
"""### Extra Trees Classifier and Random Forest are better as shwon by PyCaret."""
best_model
predict_model(best_model)
from pycaret.datasets import get_data
data = get_data(dataset)
#initialize setup
from pycaret.classification import setup, compare_models, blend_models, tune_model, save_model, deploy_model, automl
clf1 = setup(data,
target=target,
silent=True,
html=False,
log_experiment=True,
experiment_name=exp_name)
#compare models and select top5
top5 = compare_models(n_select=5, blacklist=['catboost'])
#blend top 5 models
blender = blend_models(estimator_list=top5)
#tune best model
tuned_best_model = tune_model(top5[0])
#select best model
a = automl()
save_model(a, 'best_model')
#deploy best model
deploy_model(a,
model_name='best-model-aws',
authentication={'bucket': 'pycaret-test'})
#import dataset
from pycaret.datasets import get_data
data = get_data('juice')
#init setup
from pycaret.classification import setup, compare_models, save_model, deploy_model
reg1 = setup(data,
target='Purchase',
logging=True,
experiment_name='juice-script1',
silent=True,
html=False)
#compare models
c = compare_models(n_select=1)
#save model
save_model(c, model_name='tfdemo')
#deploy model on S3
deploy_model(c,
model_name='tfdemo',
platform='aws',
authentication={'bucket': 'pycaret-test'})
# save models as .pkl files
finalize_model(etrees)
save_model(etrees, 'classifier_models(pkl)/xant_etrees')
finalize_model(xgboost)
save_model(xgboost, 'classifier_models(pkl)/xant_xgb')
finalize_model(catboost)
save_model(catboost, 'classifier_models(pkl)/xant_cboost')
finalize_model(rf)
save_model(rf, 'classifier_models(pkl)/xant_rf')
finalize_model(lgbm)
save_model(lgbm, 'classifier_models(pkl)/xant_lgbm')
finalize_model(log)
save_model(log, 'classifier_models(pkl)/xant_log')
blender_specific = blend_models(estimator_list=[etrees, lgbm, rf],
method='soft')
#blender_specific = blend_models(estimator_list=[
#etrees, lgbm, catboost], method='soft')
finalize_model(blender_specific)
save_model(blender_specific, 'classifier_models(pkl)/xant_blended')
print('PyCaret training ended \n\n')
compare_models() # print ordered 10-fold cv scores
pycset = regression.setup(data=df, target=df_target)
# Compare models
st.dataframe(regression.compare_models())
# End
st.success('End of execution!')
if df_task in ['Classification (Binary)', 'Classification (Multiclass)']:
# Setup PyCaret
with st.spinner('PyCaret setup is running...'):
pycset = classification.setup(data=df, target=df_target)
# Compare models
st.dataframe(classification.compare_models())
# End
st.success('End of execution!')
if df_task in ['NLP']:
# Setup PyCaret
with st.spinner('PyCaret setup is running...'):
pycset = nlp.setup(data=df, target=df_target)
# Compare models
#st.dataframe(classification.compare_models())
# End
st.success('End of execution!')
# define the location of the dataset
#url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/sonar.csv'
# load the dataset
#df = read_csv(url, header=None)
# set column names as the column number
n_cols = df.shape[1]
df.columns = [str(i) for i in range(n_cols)]
# setup the dataset
grid = setup(data=df,
target=df.columns[-1],
html=False,
silent=True,
verbose=False)
# evaluate models and compare models
best = compare_models()
# report the best model
print("best")
print(best)
# tune model hyperparameters on the sonar classification dataset
from pandas import read_csv
from sklearn.ensemble import ExtraTreesClassifier
from pycaret.classification import setup
from pycaret.classification import tune_model
# define the location of the dataset
#url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/sonar.csv'
# load the dataset
#df = read_csv(url, header=None)
# set column names as the column number
n_cols = df.shape[1]
def train_trad_ml_baseline(train_set_name,
val_set_name,
use_eiz=True,
demographic_features=False):
'''
Trains a ensemble based classifier on a distribution based feature representation of EI or EIZ scores to predict
whether or not a patient has an NMD
:param train_set_name: The name of the training set to use
:param val_set_name: The name of the validation set to use
:param use_eiz: Whether to use EIZ or raw EI scores
:param demographic_features: Whether to include demographic features.
:return: A dictionary with the path to the stored model and its best operating threshold.
'''
additional_features = ['Age', 'Sex', 'BMI'] if demographic_features else []
# obtain feature representations
train_set = obtain_feature_rep_ml_experiment(
train_set_name,
use_eiz=use_eiz,
additional_features=additional_features)
val_set = obtain_feature_rep_ml_experiment(
val_set_name, use_eiz=use_eiz, additional_features=additional_features)
# map to real-valued
train_set['Class'] = train_set['Class'].replace({'no NMD': 0, 'NMD': 1})
val_set['Class'] = val_set['Class'].replace({'no NMD': 0, 'NMD': 1})
# use only ensemble models
models_to_use = models(type='ensemble')
models_to_use = models_to_use.index.to_list()
# get the set of all features in the dataset
features = set(train_set.columns)
features.remove('Class')
# set the experiment up
exp = setup(train_set,
target='Class',
numeric_features=features,
html=False,
session_id=123,
train_size=0.7)
# sidestep the fact that the the lib makes another validation set
# manually get the pipeline pycaret uses for transforming the data
pipeline = exp[7]
X_train = train_set.drop(columns='Class')
# transform into the format pycaret expects
X_train = pipeline.transform(X_train)
# overwrite the selected train set to use the entire training set instead
set_config('X_train', X_train)
set_config('y_train', train_set['Class'])
# same logic with the val set, use our own instead of the pre-sliced one
X_test = val_set.drop(columns='Class')
# transform and set as the validation set
X_test = pipeline.transform(X_test)
# overwrite config
set_config('X_test', X_test)
set_config('y_test', val_set['Class'])
# obtain the best model from the list, sorted by val set AUC
best_model = compare_models(whitelist=models_to_use,
sort='AUC',
n_select=1)
# interpretability output, get SHAP plots to judge feature importance
interpret_model(best_model)
# now, do some additional tuning, compare different hyperparemters, maximize AUC
best_model = tune_model(best_model, optimize='AUC')
# interpret the best model
interpret_model(best_model)
# the path to save the model at
model_path = get_model_name(train_set_name, use_eiz, demographic_features)
# save the model
save_model(best_model, model_path)
# get results on val set as dataframe
results = predict_model(best_model, verbose=False)
# get the threshold at which the model performed best on the val set
best_threshold = evaluate_roc(results['Class'],
results['Score'],
method='val_set_training')
return {'best_threshold': best_threshold, 'model_path': model_path}
def classification_model(
*,
y_col,
training_set,
normalize,
test_size,
folds,
metric,
model_name,
testing_set,
imbalanced,
seed,
include_models,
normalize_method,
):
"""
Build a classification model for prediction.
Parameters
----------
y_col : str
the name of the target column.
training_set : pd.DataFrame
DataFrame containing the training data.
normalize : bool
if True the dataset will be normalized before training.
test_size : float
Between [0.0-1.0]. The size of the split for test within the training set.
folds : int
number of folds for cross validation.
metric : str
the metric used for evaluating the best model.
model_name : str
the name to save the model.
testing_set : pd.DataFrame
the external dataset for evaluating the best model.
imbalanced : bool
if True the imbalance will be fixed before the training.
seed : int
random number to initilize the process.
include_models : List
a list of models to be included in the process.
normalize_method : str
The method used for normalizing the data.
Returns
-------
Final classification model
"""
if not metric:
metric = 'AUC'
setup = pycl.setup(target=y_col,
fix_imbalance=imbalanced,
normalize=normalize,
normalize_method=normalize_method,
data=training_set,
train_size=1 - test_size,
silent=True,
fold=folds,
session_id=seed)
best_model = pycl.compare_models(sort=metric, include=include_models)
pycl.pull().to_csv(model_name + '_compare_models.tsv',
sep='\t',
index=False)
cl_model = pycl.create_model(best_model)
cl_tuned_model = pycl.tune_model(cl_model, optimize=metric)
pycl.pull().to_csv(model_name + '_tuned_model.tsv', sep='\t', index=False)
final_model = pycl.finalize_model(cl_tuned_model)
pycl.plot_model(final_model, plot='pr', save=True)
pycl.plot_model(final_model, plot='confusion_matrix', save=True)
pycl.plot_model(final_model, plot='feature', save=True)
pycl.save_model(final_model, model_name)
if len(testing_set.index) != 0:
unseen_predictions = test_classifier(
model_path=model_name + '.pkl',
x_set=testing_set.drop(columns=[y_col]),
y_col=testing_set[y_col],
output=model_name)
unseen_predictions.to_csv(model_name + '_external_testing_results.tsv',
sep='\t',
index=True)
return final_model
def do_modeling(self, dataFrame, pipeline_dict):
prob_type = st.selectbox('Select type of problem',
['Classification', 'Regression'])
target_variable = st.selectbox('Select target variable',
dataFrame.columns)
classification_model_library = [
'lr', 'knn', 'nb', 'dt', 'svm', 'rbfsvm', 'gpc', 'mlp', 'ridge',
'rf', 'qda', 'ada', 'gbc', 'lda', 'et', 'xgboost', 'lightgbm',
'catboost'
]
tree_based_models = [
'Random Forest Classifier', 'Decision Tree Classifier',
'Extra Trees Classifier', 'Gradient Boosting Classifier',
'Extreme Gradient Boosting', 'Light Gradient Boosting Machine',
'CatBoost Classifier'
]
classification_model_names = [
'Logistic Regression', 'K Neighbors Classifier', 'Naive Bayes',
'Decision Tree Classifier', 'SVM - Linear Kernel',
'SVM - Radial Kernel', 'Gaussian Process Classifier',
'MLP Classifier', 'Ridge Classifier', 'Random Forest Classifier',
'Quadratic Discriminant Analysis', 'Ada Boost Classifier',
'Gradient Boosting Classifier', 'Linear Discriminant Analysis',
'Extra Trees Classifier', 'Extreme Gradient Boosting',
'Light Gradient Boosting Machine', 'CatBoost Classifier'
]
classification_models = dict(
zip(classification_model_names, classification_model_library))
if st.checkbox('X and y Split'):
X = self.get_features(dataFrame, target_variable)
y = dataFrame[target_variable]
st.write('Done!')
if st.checkbox('X,y Info'):
st.write(X)
st.write(y)
if st.checkbox('Scaling of data'):
scale_X = self.do_standardScale(X)
columns = X.columns
pipeline_dict['Scaling'] = True
for col in scale_X:
X[col] = scale_X[col].values
#X.drop(columns,axis=1,inplace=True)
st.write(X)
st.write('Done!')
if st.checkbox('Dimensionality Reduction'):
if st.checkbox('PCA'):
information_loss = st.text_input(
'Enter Information loss in percentage(%)')
if st.button('PCA'):
pipeline_dict['PCA_info_loss'] = information_loss
pca_X = self.dimred_PCA(X, information_loss)
columns = X.columns
for i, val in enumerate(pca_X.T):
X[i] = val
X.drop(columns, axis=1, inplace=True)
st.write('Done!')
if st.checkbox('LDA'):
number_components = st.text_input(
'Enter the number of components')
if st.button('LDA'):
pipeline_dict['LDA_number_components'] = number_components
lda = LDA(n_components=number_components)
lda_X = lda.fit_transform(X, y)
columns = X.columns
for i, val in enumerate(lda_X.T):
X[i] = val
X.drop(columns, axis=1, inplace=True)
st.write('Done!')
if st.checkbox('Start Base-Line modeling Classification'):
py_data = X
py_data[target_variable] = y
st.write('Name :' + str(target_variable))
st.write('Type :' + str(prob_type))
if st.checkbox('Start Modeling'):
exp1 = cl.setup(data=py_data,
target=target_variable,
session_id=123,
silent=True)
st.write('Compare Models...')
#models_info = cl.create_model('lr',verbose = False)
models_info = cl.compare_models()
st.write(models_info)
if st.checkbox('Tuning Models'):
tuning_model_name = st.selectbox('Select Model for Tuning',
classification_model_names)
if st.button('Start'):
st.write(tuning_model_name)
tuned_model, result = cl.tune_model(
classification_models[tuning_model_name],
verbose=False)
st.write(result)
if tuning_model_name in tree_based_models:
cl.interpret_model(tuned_model)
st.pyplot()
cl.plot_model(tuned_model, plot='confusion_matrix')
st.pyplot()
else:
cl.plot_model(tuned_model, plot='confusion_matrix')
st.pyplot()
if st.checkbox('Finalize Model'):
final_model_name = st.selectbox('Select Model for Tuning',
classification_model_names)
if st.checkbox('Finalize'):
tuned_model, result = cl.tune_model(
classification_models[final_model_name], verbose=False)
st.write(result)
finalize_model = cl.finalize_model(tuned_model)
st.write(final_model_name)
st.write(finalize_model.get_params())
st.write('Done!')
st.write(pipeline_dict)
url = st.text_input(
"Enter Test Data Url(Must be csv file)")
if st.button('Click'):
test_dataFrame = self.get_test_data_csv(url)
st.write(test_dataFrame)
for k, v in pipeline_dict.items():
if k == 'Convert_Data_Type':
st.write('Convert_Data_Type')
self.convert_type(
test_dataFrame,
pipeline_dict['Convert_Data_Type']
['column_name'],
pipeline_dict['Convert_Data_Type']
['data_type'])
elif k == 'remove_columns':
st.write('remove_columns')
test_dataFrame.drop(
pipeline_dict['remove_columns'],
axis=1,
inplace=True)
elif k == 'remove_columns_threshold':
st.write('remove_columns_threshold..')
for threshold in pipeline_dict[
'remove_columns_threshold']:
remove_columns = self.remove_null_columns(
test_dataFrame, float(threshold))
test_dataFrame.drop(remove_columns,
axis=1,
inplace=True)
elif k == 'Fill_Median_Mode_Columns':
st.write('Fill_Median_Mode_Columns..')
test_dataFrame = self.replace_null_columns(
test_dataFrame,
pipeline_dict['Fill_Median_Mode_Columns'])
elif k == 'Create_Bins':
st.write('Create_Bins..')
column = pipeline_dict['Create_Bins'][
'column_Name']
bins = pipeline_dict['Create_Bins'][
'Numbers_bin']
for i, c in enumerate(column):
test_dataFrame[c] = self.do_bining(
test_dataFrame, c, int(bins[i]))
elif k == 'OneHotEncoding':
st.write('OneHotEncoding..')
list_columns = pipeline_dict['OneHotEncoding']
for col in list_columns:
tempdf = pd.get_dummies(
data=test_dataFrame[col])
for in_col in tempdf.columns:
colName = str(col) + '_' + str(in_col)
test_dataFrame[colName] = tempdf[
in_col].values
test_dataFrame.drop(list_columns,
axis=1,
inplace=True)
elif k == 'LabelEncoding':
st.write('LabelEncoding..')
test_dataFrame = self.do_label_Encoding(
test_dataFrame,
pipeline_dict['LabelEncoding'])
elif k == 'BinaryEncoding':
st.write('BinaryEncoding..')
binary_encoding_columns = pipeline_dict[
'BinaryEncoding']
for col in binary_encoding_columns:
encoder = ce.BinaryEncoder(cols=[col])
dfbin = encoder.fit_transform(
dataFrame[col])
for col in dfbin.columns:
test_dataFrame[col] = dfbin[col].values
test_dataFrame.drop(binary_encoding_columns,
axis=1,
inplace=True)
elif k == 'Scaling':
st.write('Scaling..')
scale_X = self.do_standardScale(test_dataFrame)
columns = test_dataFrame.columns
for col in scale_X:
test_dataFrame[col] = scale_X[col].values
st.write(test_dataFrame)
unseen_predictions = cl.predict_model(
finalize_model, data=test_dataFrame)
st.write(unseen_predictions.head())
unseen_predictions.to_csv('result.csv')
version()
import time
t0 = time.time()
#loading dataset
from pycaret.datasets import get_data
data = get_data(dataset, verbose=False)
#init regression
from pycaret.classification import setup
exp1 = setup(data, target=target, silent=True, html=False, verbose=False)
#RECEIPE #1 - SELECT TOP 5 MODELS
from pycaret.classification import compare_models
top5 = compare_models(n_select=5,
whitelist=['dt', 'lr', 'rf', 'lightgbm', 'xgboost'])
#RECEIPE #2 - TUNE TOP 5 MODELS
from pycaret.classification import tune_model
tuned_top5 = [tune_model(i) for i in top5]
print(len(tuned_top5))
#RECIPE #3
from pycaret.classification import blend_models
blender = blend_models(top5, verbose=False)
print(blender)
from pycaret.classification import pull
pull()
#FINALIZE BEST MODEL
