import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
from xgboost import XGBRegressor
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
from sklearn.ensemble import RandomForestRegressor 
from sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.preprocessing import LabelEncoder
from google.colab import drive
drive.mount('/content/drive')
df = pd.read_csv('path/beforeNeural.csv')
df.shape
df.head()
df.isnull().sum()
encoder = LabelEncoder()
df['Property Type'] = encoder.fit_transform(df['Property Type'])
df['Old/New'] = encoder fit_transform(df['Old/New'])
df['Record Status - monthly file only'] = encoder.fit_transform(df['Record Status - monthly file only'])
df['PPDCategory Type'] = encoder.fit_transform(df['PPDCategory Type'])
df['County'] = encoder.fit_transform(df['County'])
df['District'] = encoder.fit_transform(df['District'])
df['Town/City'] = encoder.fit_transform(df['Town/City'])
df['Duration'] = encoder.fit_transform(df['Duration'])
df['Transaction unique identifier'] = encoder.fit_transform(df['Transaction unique identifier'])
df['Date of Transfer'] = encoder.fit_transform(df['Date of Transfer'])
X = df.drop(columns='Price', axis=1)
Y = df['Price']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=2)
df.shape
boostenc = XGBRegressor()
boostenc.fit(X_train, Y_train)

我将尝试优化你的代码，以下是可能的优化选项，
## 代码：
```python
import pandas as pd
from xgboost import XGBRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from google.colab import drive
drive.mount('/content/drive')
df = pd.read_csv('path/beforeNeural.csv')
categorical_columns = ['Property Type', 'Old/New', 'Record Status - monthly file only', 'PPDCategory Type', 'County', 'District', 'Town/City', 'Duration', 'Transaction unique identifier', 'Date of Transfer']
encoder = OneHotEncoder()
X_concat = encoder.fit_transform(df[categorical_columns])
# 方法 1:
X_concat = pd.DataFrame(X_concat.toarray(), columns = encoder.get_feature_names(categorical_columns))
# 方法 2:
X_concat = pd.SparseDataFrame(X_concat.to_coo(), columns = encoder.get_feature_names(categorical_columns))
X_numerical = df.drop(columns = categorical_columns + ['Price'])
X = pd.concat([X_numerical, X_concat], axis = 1)
Y = df['Price']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 2)
boostenc = XGBRegressor()
boostenc.fit(X_train, Y_train)

<details>
<summary>英文:</summary>
I&#39;ll give it a try, here is a possible option to optimize your code,
## Code:
```python
import pandas as pd
from xgboost import XGBRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from google.colab import drive
drive.mount(&#39;/content/drive&#39;)
df = pd.read_csv(&#39;path/beforeNeural.csv&#39;)
categorical_columns = [&#39;Property Type&#39;, &#39;Old/New&#39;, &#39;Record Status - monthly file only&#39;, &#39;PPDCategory Type&#39;, &#39;County&#39;, &#39;District&#39;, &#39;Town/City&#39;, &#39;Duration&#39;, &#39;Transaction unique identifier&#39;, &#39;Date of Transfer&#39;]
encoder = OneHotEncoder()
X_concat = encoder.fit_transform(df[categorical_columns])
# Approach 1:
X_concat = pd.DataFrame(X_concat.toarray(), columns = encoder.get_feature_names(categorical_columns))
# Approach 2:
X_concat = pd.SparseDataFrame(X_concat.to_coo(), columns = encoder.get_feature_names(categorical_columns))
X_numerical = df.drop(columns = categorical_columns + [&#39;Price&#39;])
X = pd.concat([X_numerical, X_concat], axis = 1)
Y = df[&#39;Price&#39;]
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 2)
boostenc = XGBRegressor()
boostenc.fit(X_train, Y_train)