erdogant

# Make edits in the dataframe.
d3.edge_properties

#      label         x         y  ...   stroke  opacity                     tooltip
# 0      acc  0.796433  0.745925  ...  #000000      0.8   acc <br /> Survival: 44.5
# 1      acc  0.795550  0.739818  ...  #000000      0.8   acc <br /> Survival: 55.0
# 2      acc  0.793272  0.739995  ...  #000000      0.8   acc <br /> Survival: 63.8
# 3      acc  0.803293  0.747982  ...  #000000      0.8   acc <br /> Survival: 11.9
# 4      acc  0.793152  0.725707  ...  #000000      0.8   acc <br /> Survival: 79.7
#    ...       ...       ...  ...      ...      ...                         ...

erdogant

# Load library
from d3blocks import D3Blocks

# Initialize
d3 = D3Blocks(frame=True)
# Import example
df = d3.import_example('cancer')

# Setup the tooltip
tooltip=df['labels'].values + ' <br /> Survival: ' + df['survival_months'].astype(str).str[0:4].values

erdogant

# Create interactive scatter plot
from d3blocks import D3Blocks

# Initialize
d3 = D3Blocks()

# Make scatter
d3.scatter(map_pca[:,0],
           map_pca[:,1],
           x1=map_tsne[:,0],

erdogant

# Import library
from d3blocks import D3Blocks

# Initialize
d3 = D3Blocks()

# Make particles
d3.particles('D3Blocks', collision=0.05, spacing=10, figsize=[1200, 500])

erdogant

# Import library
from d3blocks import D3Blocks

# Initialize
d3 = D3Blocks()

# import example
df = d3.import_example('cancer')

# Tooltip

erdogant

# Save model
status = hgb.save(filepath='hgboost_model.pkl', overwrite=True)
# [pypickle] Pickle file saved: [hgboost_model.pkl]
# [hgboost] >Saving.. True

# Load model
From hgboost import hgboost                      # Import library when using a fresh start
hgb = hgboost()                                  # Initialize hgboost
results = hgb.load(filepath='hgboost_model.pkl') # Load the pickle file with model parameters and trained model.
# [pypickle] Pickle file loaded: [hgboost_model.pkl]

erdogant

##########################################
# Import Titanc dataset and preprocessing.
##########################################
df = hgb.import_example(data='titanic')

print(df)

#      PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked
# 0              1         0       3  ...   7.2500   NaN         S
# 1              2         1       1  ...  71.2833   C85         C

erdogant

# Fit
results = hgb.xgboost(X, y, pos_label=1, eval_metric='auc')
# results = hgb.catboost(X, y, pos_label=1, eval_metric='auc')
# results = hgb.lightboost(X, y, pos_label=1, eval_metric='auc')


# [hgboost] >Start hgboost classification.
# [hgboost] >Collecting xgb_clf parameters.
# [hgboost] >Correct for unbalanced classes using [scale_pos_weight]..
# [hgboost] >[13] hyperparameters in gridsearch space. Used loss function: [auc].

erdogant

#######################################################
# Import Titanic dataset, and preprocessing
#######################################################
# Import the Titanic dataset
df = hgb.import_example(data='titanic')

print(df)
#      PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked
# 0              1         0       3  ...   7.2500   NaN         S
# 1              2         1       1  ...  71.2833   C85         C

erdogant

# Import the library
from hgboost import hgboost

# Initialize library.
hgb = hgboost(
    max_eval=250,      # Search space is based  on the number of evaluations.
    threshold=0.5,     # Classification threshold. In case of two-class model this is 0.5.
    cv=5,              # k-folds cross-validation.
    test_size=0.2,     # Percentage split for the testset.
    val_size=0.2,      # Percentage split for the validationset.