Page 80 - Data Science Algorithms in a Week

Decision Trees

IG(S,wind) and IG(S,temperature) are greater than IG(S,sunshine). Both of them are equal;
therefore, we can choose any of the attribute to form the three branches; for example, the
first one, temperature. In that case, each of the three branches would have data samples S ,
cold
S warn , S . At those branches, we could apply the algorithm further to form the rest of the
hot
decision tree. Instead, we will use the program to complete the tree.
Input:

source_code/3/chess.csv
Temperature,Wind,Sunshine,Play
Cold,Strong,Cloudy,No
Warm,Strong,Cloudy,No
Warm,None,Sunny,Yes
Hot,None,Sunny,No
Hot,Breeze,Cloudy,Yes
Warm,Breeze,Sunny,Yes
Cold,Breeze,Cloudy,No
Cold,None,Sunny,Yes
Hot,Strong,Cloudy,Yes
Warm,None,Cloudy,Yes
Output:

$ python construct_decision_tree.py chess.csv 0
Root
├── [Temperature=Cold]
│ ├── [Wind=Breeze]
│ │ └── [Play=No]
│ ├── [Wind=Strong]
│ │ └── [Play=No]
│ └── [Wind=None]
│ └── [Play=Yes]
├── [Temperature=Warm]
│ ├── [Wind=Breeze]
│ │ └── [Play=Yes]
│ ├── [Wind=None]
│ │ ├── [Sunshine=Sunny]
│ │ │ └── [Play=Yes]
│ │ └── [Sunshine=Cloudy]
│ │ └── [Play=Yes]
│ └── [Wind=Strong]
│ └── [Play=No]
└── [Temperature=Hot]
├── [Wind=Strong]
│ └── [Play=Yes]
├── [Wind=None]
│ └── [Play=No]

[ 68 ]