PranjalDureja0002

res_dim = 1024

if __name__ == "__main__":
    """loading the data, 
    reading the file annotations,
    appending the tabular coordinates to formulate a dataframe
    """
    df_org = pd.DataFrame()  
    directory = '/content/drive/MyDrive/data_cs2'
    final_col_directory = '/content/drive/MyDrive/cs2_col'

PranjalDureja0002

res_dim = 1024

if __name__ == "__main__":
    """loading the data, 
    reading the file annotations,
    appending the tabular coordinates to formulate a dataframe
    """
    df_org = pd.DataFrame()  
    directory = '/content/drive/MyDrive/data_cs2'
    final_col_directory = '/content/drive/MyDrive/cs2_col'

PranjalDureja0002

<annotation verified="yes">
	<folder>MARMOT_ANNOTATION</folder>
	<filename>10.1.1.1.2006_3.bmp</filename>
	<path>/home/monika/Desktop/MARMOT_ANNOTATION/10.1.1.1.2006_3.bmp</path>
	<source>
		<database>Unknown</database>
	</source>
	<size>
		<width>793</width>
		<height>1123</height>

PranjalDureja0002

def final_fun_1(X):
    """ function takes raw data as input,preprocessing is done,
    feature engineering is performed and predictions made on the
    best model already trained"""
            
    d_beneficiary = pd.read_csv('health_cs_data/' + X[0])
    d_inpatient = pd.read_csv('health_cs_data/' + X[1])
    d_outpatient = pd.read_csv('health_cs_data/' + X[2])
    d_labels = pd.read_csv('health_cs_data/' + X[3])
    

PranjalDureja0002

	providerID	y_predicted
0	PRV57070	  0
1	PRV57070	  1
2	PRV57070	  0
3	PRV57070	  0
4	PRV57070	  0
5	PRV57070	  1
6	PRV57070	  0
7	PRV57070	  1
8	PRV57070	  0

PranjalDureja0002

def final_fun_1(X):
    """ function takes raw data as input,preprocessing is done,
    feature engineering is performed and predictions made on the
    best model already trained"""
            
    d_beneficiary = pd.read_csv('health_cs_data/' + X[0])
    d_inpatient = pd.read_csv('health_cs_data/' + X[1])
    d_outpatient = pd.read_csv('health_cs_data/' + X[2])
    d_labels = pd.read_csv('health_cs_data/' + X[3])
    

PranjalDureja0002

def find_best_threshold(threshold, fpr, tpr):
    t = threshold[np.argmax(tpr*(1-fpr))]     
    print("the maximum value of tpr*(1-fpr)", max(tpr*(1-fpr)), "for threshold", np.round(t,3))
    return t

def predict_with_best_t(proba, threshold):
    predictions = []
    for i in proba:                              
        if i>=threshold:
            predictions.append(1)

PranjalDureja0002

+---------+-----------------+----------------+----------------+---------------+
|  Model  | Train AUC Score | Test AUC Score | Train F1 Score | Test F1 Score |
+---------+-----------------+----------------+----------------+---------------+
| XgBoost |     0.99938     |    0.99855     |     0.9998     |    0.990791   |
+---------+-----------------+----------------+----------------+---------------+ +---------------+-----------------+----------------+----------------+---------------+
|     Model     | Train AUC Score | Test AUC Score | Train F1 Score | Test F1 Score |
+---------------+-----------------+----------------+----------------+---------------+
| Decision_Tree |      0.9967     |     0.9909     |    0.99314     |     0.9771    |
+---------------+-----------------+----------------+----------------+---------------+ +---------------------+-----------------+----------------+----------------+---------------+
|        Model        | Train AUC Score | Test AUC Score | Train F1 Score | Test F1 Score |

PranjalDureja0002

#In the 80% train set, split the train set into d1 and d2.(50-50).
d1,d2,y1,y2 = train_test_split(X_train,y_train,stratify=y_train,test_size=0.5,random_state=15)
d1 = d1.reset_index(drop=True)
d2 = d2.reset_index(drop=True)
y1 = y1.reset_index(drop=True)
y2 = y2.reset_index(drop=True)

def generating_samples(d1, y1):
    """From this d1,sampling with replacement is done
    """

PranjalDureja0002

+--------------------------------+-------------+---------------+
| Custom_Stacking_Implementation | Base Models | Test F1 Score |
+--------------------------------+-------------+---------------+
|                                |      50     |    0.980001   |
|                                |     100     |    0.981479   |
|                                |     150     |    0.982725   |
+--------------------------------+-------------+---------------+