when i use the code, the print is always the iris.data' result although i change the data.

[liariel]

Hi ChawlaAvi, when i use the code, the print is always the iris.data' result although i change the data.

`import pandas as pd
import numpy as np
import interactive_decision_tree as idt ## local module
from sklearn.tree import DecisionTreeClassifier

data = pd.read_csv('/Users/lee/Desktop/data-xy015.csv')
X = data.iloc[:, 0:31]
y = data.iloc[:, 38]

clf = DecisionTreeClassifier()
clf = clf.fit(X, y)

idt.create_tree(tree_model=clf,
X=X,
target_names=np.unique(y),
save_path='C:/Users/lee/Desktop/PY01/tree_template.html')

idt.create_sankey(tree_model=clf,
X=X,
target_names=np.unique(y),
save_path='C:/Users/lee/Desktop/PY01/sankey_template.html')
`

[shreevaths1]

Have you used iris dataset in above code ? Does /Users/lee/Desktop/data-xy015.csv refer to iris dataset ?

[liariel]

Hi shreevaths1, I didn't use the iris dataset. "/Users/lee/Desktop/data-xy015.csv" is about my experiment data.
I also custom decision tree model, the print is still the iris.data' result.

import pandas as pd
import numpy as np
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.preprocessing import MinMaxScaler
from sklearn.tree import DecisionTreeClassifier
import interactive_decision_tree as idt

class MyDecisionTree:
def init(self):
self.tree = None

def fit(self, X, y):
    self.tree = DecisionTreeClassifier(criterion="gini", random_state=100, max_depth=4, min_samples_leaf=0.05, max_leaf_nodes=50)
    self.tree.fit(X, y)

def predict(self, X):
    return self.tree.predict(X)

def importdata():
balance_data = pd.read_csv('/Users/lee/Desktop/data-xy015.csv', sep=',', header=0)
print("Dataset Length: ", len(balance_data))
print("Dataset Shape: ", balance_data.shape)
print("Dataset: ", balance_data.head())
return balance_data

def splitdataset(balance_data):
X = balance_data.values[:, 0:30]
Y = balance_data.values[:, 38]
scaler = MinMaxScaler()
X = scaler.fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=100)
return X, Y, X_train, X_test, y_train, y_test

def train_using_gini(X_train, X_test, y_train):
clf_gini = MyDecisionTree()
clf_gini.fit(X_train, y_train)
return clf_gini

def prediction(X_test, clf_object):
y_pred = clf_object.predict(X_test)
print("Predicted values:")
print(y_pred)
return y_pred

def cal_accuracy(y_test, y_pred):
print("Confusion Matrix: ", confusion_matrix(y_test, y_pred))
print("Accuracy : ", accuracy_score(y_test, y_pred) * 100)
print("Report : ", classification_report(y_test, y_pred))

def build_decision_tree(X, clf_object):
feature_names = ['X1', 'X2', 'X3', 'X4', 'X5', 'X6', 'X7', 'X8', 'X9', 'X10', 'X11', 'X12', 'X13', 'X14', 'X15',
'X16', 'X17', 'X18', 'X19', 'X20', 'X21', 'X22', 'X23', 'X24', 'X25', 'X26', 'X27', 'X28',
'X29', 'X30']
class_names = ['low', 'high']
idt.create_sankey(tree_model=clf_object.tree, X=X, target_names=class_names, save_path='/Users/lee/Desktop/tree_template1.html')

def main():
data = importdata()
X, Y, X_train, X_test, y_train, y_test = splitdataset(data)
clf_gini = train_using_gini(X_train, X_test, y_train)
print("Results Using Gini Index:")
y_pred_gini = prediction(X_test, clf_gini)
cal_accuracy(y_test, y_pred_gini)
build_decision_tree(X, clf_gini)

if name == "main":
main()