数据处理与分析技术-题库 (2)

clf.______________

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.tree import DecisionTreeClassifier

from sklearn.metrics import accuracy_score

iris = load_iris()

X, y = iris.data, iris.target

X_train, X_test, y_train, y_test = train_test_split(

X, y, train_size=0.8, random_state=0)

clf = DecisionTreeClassifier(criterion=________)

clf.fit( ________, ________ )

y_pred = clf.predict(X_test)

print(accuracy_score(y_test, y_pred))

from sklearn.tree import export_graphviz

import pydotplus

dot_data = export_graphviz(

model,

out_file=____,

feature_names=['aveSpeed','stopNum'],

class_names=['畅通','缓行','拥堵'],

filled=True, rounded=True)

graph = pydotplus.____(dot_data)

graph.write_png('tree.png')

import pandas as pd

from sklearn.cluster import KMeans

from sklearn.preprocessing import StandardScaler

data = pd.read_csv('traffic.csv')

X = data[['aveSpeed', 'stopNum']]

scaler = StandardScaler()

X_std = scaler.【_______】(X) # 训练并转换

labels = KMeans(n_clusters=【______】, random_state=0).fit(X_std).【______】

out = pd.concat([data, pd.Series(labels, name='label')], axis=1)

out.to_csv('kmeans_result.csv', index=False)

from sklearn.cluster import DBSCAN

db = DBSCAN(eps=【_____】, min_samples=【______】)

labels = db.fit_predict(X_std)

# 统计噪声点数量

noise_num = sum(labels == 【______】)

# 1. 导入数据处理库

import (1) ______ as pd

# 2. 读取数据集（csv名为DATASET-B.csv）

data = pd.read_csv( (2) ______ )

# 3. 转换特定列的数据类型为整数

for c in ['rowid', 'colid', 'time_id']:

data[c] = data[c].astype(int)

# 4. 按指定字段排序并重置索引

data = data. (3) ______ (['date', 'rowid', 'colid', 'time_id']).reset_index(drop=True)

# 5. 转换日期格式并提取星期信息

data['datetime'] = pd.to_datetime(data.date, format='%Y%m%d')

data['dayofweek'] = data.datetime.dt. (4) ______

# 6. 随机抽样5000条数据

data = data. (5) ______ (5000, random_state=233)

# 7. 导入数据集划分工具

from sklearn. (6) ______ import train_test_split

# 8. 划分训练集（70%）和测试集（30%）

train, test = train_test_split(data, test_size=0.3, random_state=233)

# 9. 导入随机森林分类器

from sklearn. (7) ______ import RandomForestClassifier

# 10. 初始化随机森林模型

rf = RandomForestClassifier(

n_estimators=256,

max_depth=9,

min_samples_leaf=30,

n_jobs=-1,

random_state=233

)

# 11. 指定特征列

features = [

'rowid', 'colid', 'time_id', 'dayofweek',

'aveSpeed', 'gridAcc', 'volume', 'speed_std', 'stopNum'

]

# 12. 训练模型

rf.fit(train[features], train['labels'])

# 13. 计算训练集精度

rf_train_score = rf.score( (8) ______ , train['labels'])

# 14. 计算测试集精度

rf_test_score = rf.score( (9) ______ , test['labels'])

# 15. 打印模型精度结果

print(f'随机森林模型精度：训练集：{rf_train_score:.3f}；测试集：{rf_test_score:.3f}')