COMP1942 Project Phase 2
Training data set: Sheet1!A1:I9946 (First row contains headers)
Test data set: Sheet2!A1:H3016 (First row contains headers)
Model 1: Decision Tree Classifier
Input variables: parent-occupation, child-nursery, form-of-the-family, no-of-children,
housing-condition, finance-standing-of-the-family, social-condition, health-condition
Output variable: success
Data range: Sheet1!A1:I9946
Parameter:
# Classes: 2
Specify “Success” class (for Lift Chart): yes
Specify initial cutoff probability value for success: 0.5
Normalize input data: no
Minimum #records in a terminal node: 100
Score training data: Detailed report, Summary report, Lift charts
Score new data: In worksheet
Model 2: Decision Tree Classifier
Input variables: parent-occupation, child-nursery, form-of-the-family, no-of-children,
housing-condition, finance-standing-of-the-family, social-condition, health-condition
Output variable: success
Data range: Sheet1!A1:I9946
Parameter:
# Classes: 2
Specify “Success” class (for Lift Chart): yes
Specify initial cutoff probability value for success: 0.5
Normalize input data: yes
Minimum #records in a terminal node: 100
Score training data: Detailed report, Summary report, Lift charts
Score new data: In worksheet
Model 3: Naïve Bayes Classifier
Input variables: parent-occupation, child-nursery, form-of-the-family, no-of-children,
housing-condition, finance-standing-of-the-family, social-condition, health-condition
Output variable: success
Data range: Sheet1!A1:I9946
This study source was downloaded by 100000787037251 from CourseHero.com on 04-09-2024 00:11:40 GMT -05:00
https://www.coursehero.com/file/12852697/Project-Phase-2/
Parameter:
# Classes: 2
Specify “Success” class (for Lift Chart): yes
Specify initial cutoff probability value for success: 0.5
Prior class probabilities: According to relative occurrences in training data
Score training data: Detailed report, Summary report, Lift charts
Score new data: In worksheet
Model 4: Naïve Bayes Classifier
Input variables: parent-occupation, child-nursery, form-of-the-family, no-of-children,
housing-condition, finance-standing-of-the-family, social-condition, health-condition
Output variable: success
Data range: Sheet1!A1:I9946
Parameter:
# Classes: 2
Specify “Success” class (for Lift Chart): no
Specify initial cutoff probability value for success: 0.5
Prior class probabilities: According to relative occurrences in training data
Score training data: Detailed report, Summary report, Lift charts
Score new data: In worksheet
Model 5: Nearest Neighbor Classifier
Input variables: parent-occupation, child-nursery, form-of-the-family, no-of-children,
housing-condition, finance-standing-of-the-family, social-condition, health-condition
Output variable: success
Data range: Sheet1!A1:I9946
Parameter:
# Classes: 2
Specify “Success” class (for Lift Chart): no
Specify initial cutoff probability value for success: 0.5
Normalize input data: no
Number of nearest neighbors (k): 1001
Scoring option: Score on specified value of k as above
Score training data: Detailed report, Summary report, Lift charts
Score new data: In worksheet
This study source was downloaded by 100000787037251 from CourseHero.com on 04-09-2024 00:11:40 GMT -05:00
https://www.coursehero.com/file/12852697/Project-Phase-2/
Powered by TCPDF (www.tcpdf.org)