class DecisionTreeAsWeakClassifier(WeakClassifier):
def __init__(self, model, label_mapping):
self.classifier = DecisionTreeModel()
self.classifier.set_max_depth(2)
self.model = model
self.label_mapping = label_mapping
def fit(self, data):
# print(data)
self.classifier.fit(data=data, algo_model=self.model)
def predict(self, X):
pre = self.classifier.predict(X)
return np.array([self.label_mapping.get(y) for y in pre])
def mapping_label(self, Y):
return np.array([self.label_mapping.get(x) for x in Y])
## wine dataset
# data = np.loadtxt(ROOT_DIR+"/../wine/wine_data.csv", dtype=str, delimiter=",", skiprows=0)
## iris dataset
# data = np.loadtxt(ROOT_DIR+"/../iris/iris_data.csv", dtype=str, delimiter=",", skiprows=0)
## car dataset
data = np.loadtxt(ROOT_DIR + "/../car/car_data.csv",
dtype=str,
delimiter=",",
skiprows=0)
data = data[:, 1:]
print("... no-pruning ...")
model = DecisionTreeModel()
model.fit(data=data, algo_model="cart", split_ratio="9:1")
# print(model.root["feature"])
# print(json.dumps(model.root, indent=4, ensure_ascii=False))
dot = model.export_graphviz()
report = model.report_performances()
print(report)
## pre_pruning
print("... pre-pruning ...")
pre_pruning_model = DecisionTreeModel()
pre_pruning_model.fit(data=data,
algo_model="cart",
split_ratio="9:1",
prune="pre")
pre_pruning_dot = pre_pruning_model.export_graphviz(dot)
import os
ROOT_DIR = os.path.abspath(os.path.dirname(__file__))
sys.path.append(ROOT_DIR+"/../Model")
from decision_tree_model import DecisionTreeModel
import numpy as np
import json
import graphviz
from sklearn import tree
if __name__ == "__main__":
# data = np.loadtxt(ROOT_DIR+"/../watermelon/watermelon_2.0.csv", dtype=str, delimiter=",", skiprows=0)
data = np.loadtxt(ROOT_DIR+"/../watermelon/watermelon_3.0.csv", dtype=str, delimiter=",", skiprows=0)
# data = np.loadtxt(ROOT_DIR+"/../watermelon/watermelon_3.0_x.csv", dtype=str, delimiter=",", skiprows=0)
data = data[:,1:]
# print(data)
model = DecisionTreeModel()
model.fit(data=data, algo_model="id3")
# print(model.root["feature"])
# print(json.dumps(model.root, indent=4, ensure_ascii=False))
## predict train
x = data[1:,:-1]
y = data[1:,-1]
# x = x[8:9,:]
# y = y[8:9]
print("---------------my own.DecisionTreeClassifier----------------")
predictions = model.predict(x)
print("Y:{}".format(",".join(y)))
print("Predictions:{}".format(",".join(predictions)))
print("train accuracy:{}".format(model.accuracy(y, predictions)))
import json
if __name__ == "__main__":
data = np.loadtxt(ROOT_DIR + "/../watermelon/watermelon_2.0_x.csv",
dtype=str,
delimiter=",",
skiprows=0)
# data = np.loadtxt(ROOT_DIR+"/../wine/wine_data.csv", dtype=str, delimiter=",", skiprows=0)
data = data[:, 1:]
# print(data)
# model = DecisionTreeModel()
# model.fit(data=data, algo_model="id3")
# model.fit(data=data, algo_model="cart")
# model.fit(data=data, algo_model="cart", split_ratio="watermelon")
# model.fit(data=data, algo_model="cart", split_ratio="9:1")
# print(model.root["feature"])
# print(json.dumps(model.root, indent=4, ensure_ascii=False))
# dot = model.export_graphviz()
# dot.render(view=True, cleanup=True)
## post_pruning
post_pruning_model = DecisionTreeModel()
post_pruning_model.fit(data=data,
algo_model="cart",
split_ratio="watermelon",
prune="post")
post_pruning_dot = post_pruning_model.export_graphviz()
post_pruning_dot.render(view=True, cleanup=True)
ROOT_DIR = os.path.abspath(os.path.dirname(__file__))
sys.path.append(ROOT_DIR + "/../Model")
from decision_tree_model import DecisionTreeModel
import numpy as np
import json
if __name__ == "__main__":
data = np.loadtxt(ROOT_DIR + "/../watermelon/watermelon_2.0_x.csv",
dtype=str,
delimiter=",",
skiprows=0)
# data = np.loadtxt(ROOT_DIR+"/../watermelon/watermelon_3.0_x.csv", dtype=str, delimiter=",", skiprows=0)
# data = np.loadtxt(ROOT_DIR+"/../wine/wine_data.csv", dtype=str, delimiter=",", skiprows=0)
data = data[:, 1:]
# print(data)
model = DecisionTreeModel()
# model.fit(data=data, algo_model="id3")
# model.fit(data=data, algo_model="cart")
model.fit(data=data, algo_model="cart", split_ratio="watermelon")
# model.fit(data=data, algo_model="cart", split_ratio="9:1")
# print(model.root["feature"])
print(json.dumps(model.root, indent=4, ensure_ascii=False))
## predict train
x = data[1:, :-1]
y = data[1:, -1]
predictions = model.predict(x)
print(",".join(predictions))
print(",".join(y))
print("train accuracy:{}".format(model.accuracy(y, predictions)))
def __init__(self, model, label_mapping):
self.classifier = DecisionTreeModel()
self.classifier.set_max_depth(2)
self.model = model
self.label_mapping = label_mapping