tencent cloud

#Install the driver.
!pip install tencentcloud-dlc-connector
!pip  install --upgrade 'sqlalchemy<2.0'

#Installation version.
!pip install --upgrade pandas==2.2.3
!pip install numpy
!pip install matplotlib
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
import tdlc_connector
from tdlc_connector import constants
import mlflow
mlflow.sklearn.autolog()

#Use tdlc-connector to access in table mode.
conn = tdlc_connector.connect(region="ap-***", #Fill in the correct address, for example: ap-Singapore and ap-Shanghai
    secret_id="*******", 
    secret_key="*******",
    engine="your engine", #Fill in the purchased engine name.
    resource_group=None,
    engine_type=constants.EngineType.AUTO, 
    result_style=constants.ResultStyles.LIST,
    download=True
    )
query = """
SELECT sepal.length, sepal.width,petal.length,petal.width,species FROM at_database_testnotebook.demo_test_sklearn
"""


#Read data.
iris = pd.read_sql(query, conn)
iris.head()
#Divide the dataset.
X = iris[['petal.length', 'petal.width']].values
category_map = {
    'setosa': 0,
    'versicolor': 1,
    'virginica': 2
}

y= iris['species'].replace(category_map)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=1, stratify=y)  
print('Labels count in y:', np.bincount(y))
print('Labels count in y_train:', np.bincount(y_train))
print('Labels count in y_test:', np.bincount(y_test))

#Data normalization.
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))

#Perform logistic regression classification, and visualize the classification result.
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(C=100.0, random_state=1, solver='lbfgs', multi_class='ovr')
lr.fit(X_train_std, y_train)

plot_decision_regions(X_combined_std, y_combined,
                      classifier=lr, test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()

#View model accuracy.
y_pred = lr.predict(X_test_std)
print(accuracy_score(y_test, y_pred))