def baseline_model(self, scoring, SEED, result_col_nm):
# Run the baseline models on the unbalanced dataset
models = f.GetBasedModel()
names, results = f.get_model_performance(self.X_train, self.y_train,
models, SEED, scoring)
f.PlotBoxR().PlotResult(names, results)
_score = f.ScoreDataFrame(names, results, result_col_nm)
return _score
get_highly_corr_feats = pd.DataFrame(get_highly_corr_feats)
print('Highly correlated features description more than pearsonsr',
corr_threshold)
get_highly_corr_feats
### Create Base Model with default hyperparameters and all features #####
SEED = 7
X = x_df_dum.drop(train_df[['TARGET', 'SK_ID_CURR']], axis=1)
Y = x_df_dum[['TARGET']]
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size=0.25, random_state=0, stratify=x_df_dum['TARGET'])
# Run the baseline models on the unbalanced dataset
models = f.GetBasedModel()
names, results = f.get_model_performance(X_train, y_train, models, SEED,
'f1_weighted')
f.PlotBoxR().PlotResult(names, results)
basedLineF1Score = f.ScoreDataFrame(names, results, 'baseline_f1_Score')
models = f.GetBasedModel()
names, results = f.get_model_performance(X_train, y_train, models, SEED,
'accuracy')
f.PlotBoxR().PlotResult(names, results)
basedLineAccuracyScore = f.ScoreDataFrame(names, results, 'baseline_accuracy')
# Record Scores
ScoreCard = pd.concat([basedLineAccuracyScore, basedLineF1Score], axis=1)
# Scaled Model on top of baseline
def scaled_model(self, scoring, SEED, result_col_nm, scalar):
models = f.GetScaledModel(scalar)
names, results = f.get_model_performance(self.X_train, self.y_train,
models, SEED, scoring)
_score = f.ScoreDataFrame(names, results, result_col_nm)
return _score