dongr0510

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.metrics import roc_auc_score
from sklearn.metrics import classification_report
from sklearn.datasets import make_multilabel_classification
from xgboost import XGBClassifier
from sklearn.model_selection import KFold

dongr0510

cr_y1 = classification_report(ytest[:,0],yhat[:,0])
cr_y2 = classification_report(ytest[:,1],yhat[:,1])
cr_y3 = classification_report(ytest[:,2],yhat[:,2])
cr_y4 = classification_report(ytest[:,3],yhat[:,3])
cr_y5 = classification_report(ytest[:,4],yhat[:,4])

print (cr_y1)

-----------------------------
             precision    recall  f1-score   support

dongr0510

cm_y1 = confusion_matrix(ytest[:,0],yhat[:,0])
cm_y2 = confusion_matrix(ytest[:,1],yhat[:,1])
cm_y3 = confusion_matrix(ytest[:,2],yhat[:,2])
cm_y4 = confusion_matrix(ytest[:,3],yhat[:,3])
cm_y5 = confusion_matrix(ytest[:,4],yhat[:,4])

print (cm_y1)

---------------
[[1053  140]

dongr0510

auc_y1 = roc_auc_score(ytest[:,0],yhat[:,0])
auc_y2 = roc_auc_score(ytest[:,1],yhat[:,1])
auc_y3 = roc_auc_score(ytest[:,2],yhat[:,2])
auc_y4 = roc_auc_score(ytest[:,3],yhat[:,3])
auc_y5 = roc_auc_score(ytest[:,4],yhat[:,4])

print("ROC AUC y1: %.4f, y2: %.4f, y3: %.4f, y4: %.4f, y5: %.4f" % (auc_y1, auc_y2, auc_y3, auc_y4, auc_y5))

-------------------------------------------------------
ROC AUC y1: 0.8230, y2: 0.8025, y3: 0.8091, y4: 0.8005, y5: 0.8086

dongr0510

classifier = MultiOutputClassifier(XGBClassifier())

clf = Pipeline([('classify', classifier)])

print (clf)

------------------------------------------------
Pipeline(steps=[('classify',
                 MultiOutputClassifier(estimator=XGBClassifier(base_score=None,
                                                               booster=None,

dongr0510

for i in range(5): 
    print(x[i]," =====> ", y[i])
 

----------------------------------------------------------------------------------
[5. 4. 0. 4. 3. 0. 1. 1. 0. 3. 0. 1. 6. 0. 0. 2. 0. 1. 6. 1.]  =====>  [1 0 0 0 0]
[2. 2. 0. 1. 5. 1. 2. 0. 7. 4. 1. 0. 2. 1. 5. 2. 0. 4. 0. 6.]  =====>  [0 0 0 0 1]
[3. 4. 2. 1. 4. 5. 2. 2. 4. 1. 1. 2. 3. 5. 2. 3. 0. 4. 5. 2.]  =====>  [0 1 0 1 0]
[0. 5. 2. 3. 2. 3. 7. 4. 4. 1. 3. 0. 5. 5. 2. 1. 3. 3. 2. 3.]  =====>  [0 0 0 0 0]
[3. 6. 2. 3. 2. 0. 1. 3. 2. 4. 0. 0. 3. 4. 1. 6. 0. 5. 0. 8.]  =====>  [1 0 0 0 1]

dongr0510

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.metrics import roc_auc_score
from sklearn.metrics import classification_report
from sklearn.datasets import make_multilabel_classification
from xgboost import XGBClassifier
from sklearn.model_selection import KFold

dongr0510

def longestPalindrome(s):
    return find_LPS_recursive(st, 0, len(st)-1)

def find_LPS_recursive(s, s_Index, e_Index):
    
    if s_Index > e_Index:
        return 0
    
    if s_Index = endIndex:
        return 1

dongr0510

# Basic Solution

def calFib(n):
  if n < 2:
    return n
  return calFib(n-1) + calFib(n-2)


# Top-down DP with Memorization
def calculateFibonacci(n):

dongr0510

def unbound_knapsack(profits, weights, capacity):
    n = len(profits)
    
    # base case
    if capacity <= 0 or n == 0 or len(weights) != n:
        return 0
    
    dp = [[-1 for _ in range(capacity+1)] for _ in range(len(profits))]
    
    # initiaite the capacity = 0 columns