33 lines
1.0 KiB
Python
33 lines
1.0 KiB
Python
|
import pandas as pd
|
||
|
|
from sklearn.cluster import AgglomerativeClustering
|
||
|
|
from sklearn.preprocessing import StandardScaler
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
|
||
|
|
# Загрузка данных
|
||
|
|
df = pd.read_csv('economica.csv')
|
||
|
|
|
||
|
|
# Выбор переменных для кластеризации
|
||
|
|
selected_columns = ['gdppercent', 'oil_prices']
|
||
|
|
|
||
|
|
# Предварительная обработка данных
|
||
|
|
X = df[selected_columns]
|
||
|
|
|
||
|
|
# Заполнение пропущенных значений
|
||
|
|
X.fillna(X.mean(), inplace=True)
|
||
|
|
|
||
|
|
# Стандартизация данных
|
||
|
|
scaler = StandardScaler()
|
||
|
|
X_scaled = scaler.fit_transform(X)
|
||
|
|
|
||
|
|
# Кластеризация методом linkage
|
||
|
|
cluster = AgglomerativeClustering(n_clusters=3, linkage='ward')
|
||
|
|
df['cluster'] = cluster.fit_predict(X_scaled)
|
||
|
|
|
||
|
|
# Визуализация кластеров
|
||
|
|
plt.scatter(X_scaled[:, 0], X_scaled[:, 1], c=df['cluster'], cmap='Dark2')
|
||
|
|
plt.xlabel('GDP Percent (Standardized)')
|
||
|
|
plt.ylabel('Oil Prices (Standardized)')
|
||
|
|
plt.title('Clustering Results')
|
||
|
|
plt.savefig(f"result.png")
|
||
|
|
plt.show()
|