SyntaxError: I want to resolve invalid character identifier [overlapping]

File"<ipython-input-18-06795348b04f>", line 93
    model3=DecisionTreeClassifier(criterion='entropy', max_depth=3, random_state=0)
                                                                                     ^
SyntaxError: invalid character identifier

import pandas as pd
# Load data in Pandas.ExcelFile
input_book=pd.ExcelFile('FIFA19_data.xlsx')

input_sheet_name = input_book.sheet_names
num_sheet=len(input_sheet_name)
print(input_sheet_name)
print("Number of sheets:", num_sheet)
input_sheet_df = input_book.parse(input_sheet_name[0])

# Remove only GK data
input_sheet_df = input_sheet_df [ input_sheet_df ['Position']!="GK" ]
# Display only the first 10 lines
input_sheet_df.head(10)

import numpy as np

# load data
age=input_sheet_df.Age#age
all=input_sheet_df.Overall#comprehensive capability
message=input_sheet_df.Wage#salary
PreferredFoot=input_sheet_df.PreferredFoot#straightforward
Reputation = input_sheet_df.Reputation# Reputation
last_contract = input_sheet_df.least_contract # remaining years of engagement
crossing = input_sheet_df.Crossing #CrossingAccuracy
Finishing=input_sheet_df.Finishing#FinishingAccuracy
heading=input_sheet_df.HeadingAccuracy #HeadingAccuracy
ShortPassing=input_sheet_df.ShortPassing#ShortPassing Accuracy
Drivebling=input_sheet_df.Drivebling#DribblingAccuracy
Curve=input_sheet_df.Curve#Curve#Curve Accuracy
FKAccuracy = input_sheet_df.FKAccuracy #FK Accuracy
LongPassing=input_sheet_df.LongPassing#LongPassing #Accuracy
BallControl=input_sheet_df.BallControl#BallControl
Acceleration=input_sheet_df.Acceleration#jumpout
SprintSpeed=input_sheet_df.SprintSpeed#SprintSpeed
Agility=input_sheet_df.Agility#agility
Reactions = input_sheet_df.Reactions # Reactions
Balance=input_sheet_df.Balance#Balance
ShotPower= input_sheet_df.ShotPower#ShootPower
stamina = input_sheet_df.Stamina #stamina
Jumping=input_sheet_df.Jumping#Jump
Strength = input_sheet_df.Strength #Strength
LongShots=input_sheet_df.LongShots#LongShots
Aggression=input_sheet_df.Aggression#aggression
Interceptions=input_sheet_df.Intercepts#Intercepts
Positioning = input_sheet_df. Positioning
Vision=input_sheet_df.Vision
Penalties = input_sheet_df.Penalties
Composure=input_sheet_df.Composition
Marking = input_sheet_df.Marking
StandingTackle= input_sheet_df. StandingTackle
SlidingTackle=input_sheet_df.SlidingTackle

# specify parameters to use
equation_df2 = pd.concat([wage, age, PreferredFoot, Reputation, last_contract, \
                        crossing, finishing, heading, ShortPassing, Driving, Curve, FKAccuracy, \
                       LongPassing, BallControl, Acceleration, SprintSpeed, Agility, Reactions, \
                       Balance, ShotPower, stamina, jumping, Strength, LongShots, Aggression, \
                       Interceptions, Positioning, Vision, Penalty, Composure, Marking, \
                       StandingTackle, SlidingTackle], Axis=1)

# take out the variables to be explained
message2 = pd.DataFrame(equation_df2.Wage)
# extract the explained variable
x_list2 =equation_df2.drop("Wage", 1)

from sklearn import preprocessing, linear_model
import sklearn
import seaborn as sns

# perform data shaping
# standardize data
sc = preprocessing.StandardScaler()
sc.fit(x_list2)

X = sc.transform(x_list2)

# check the correlation coefficient

import matplotlib.pyplot asplt

plt.figure(figsize=(30,24))
sns.heatmap(x_list2.pct_change().corr(),not=True,cmap='Blues')

from sklearn import model_selection
# divide into study and test data
# Work 2:8 for split percentage
X_train, X_test, Y_train, Y_test=model_selection.train_test_split(x,wage,test_size=0.2,ramdom_state=0)

from sklearn.tree import DecisionTreeClassifier

# Conduct decision tree analysis based on X_train and Y_train values
model3=DecisionTreeClassifier(criterion='entropy', max_depth=3, random_state=0)　
model3.fit(X_train,Y_train)

print('correct answer rate (train): {:.3f}'.format(model3.score(X_train,Y_train)))
print('correct answer rate (train): {:3f}'.format(model3.score(X_test,Y_test)))