Following is my code I am running it on IDLE python 3.8

import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.feature_extraction import DictVectorizer
from sklearn import trees
from sklearn.metrics import accuracy_score,classification_report
import warnings
from sklearn.preprocessing import StandardScalar
from sklearn.neural_networks import MLPClassifier

warnings.filterwarnings(action='ignore',category=DeprecationWarning)

data=pd.read_csv('data.csv')
cols_to_retain=[]

x-feature=data[cols_to_retain]
x_dict=x_feature.T.to_dict.values()

vect=DictVectorizer(sparse=False)
x_vector=vect.fit_transform(x_dict)
print(x_vector)

x_train=[:-1]
x_test=[-1:]
print('Train set')
print(x_train)
print('Test set')
print(x_test)

le=LabelEncoder
y_train=le.fit_transform(data['Goal'][:-1])

clf=tree.DecisionTreeClassifier(criteron='entropy')
clf=clf.fit_transform(x_train,y_train)
print('Test Data')
print(le.inverse_transform(clf.predict(x_test)))

It shows me error for these particular lines It only says invalid syntax error

x_train=[:-1]
x_test=[-1:]

packages are imported correctly

CodePudding user response：

Your code contains multiple issues:

• The import should be StandardScaler not StandardScalar,
• You got unused imports like MLPClassifier,
• cols_to_retrain is empty. Thus, data[cols_to_retrain] will return an empty data frame,
• to_dict should be to_dict(),
• variable names x-feature and x_feature do not match,
• LabelEncoder is missing brackets (),
• x_train=[:-1] and x_test=[-1:] is not valid. You probably wanted to select a subset like x_train = x_vector[:-1] or x_test = x_vector[-1:]. Please add additional sample data, if you need help with this selection.

Here is an updated version of your code:

import numpy as np
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.metrics import accuracy_score, classification_report
from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.tree import DecisionTreeClassifier

data = pd.read_csv("data.csv")
print(data)
cols_to_retain = []

x_feature = data[cols_to_retain]
x_dict = x_feature.T.to_dict().values()

vect = DictVectorizer(sparse=False)
x_vector = vect.fit_transform(x_dict)
print(x_vector)

x_train = x_vector[:-1]
x_test = x_vector[-1:]
print("Train set")
print(x_train)
print("Test set")
print(x_test)

le = LabelEncoder()
y_train = le.fit_transform(data["Goal"][:-1])

clf = DecisionTreeClassifier(criteron="entropy")
clf = clf.fit_transform(x_train, y_train)
print("Test Data")
print(le.inverse_transform(clf.predict(x_test)))