大数据技术的未来应用场景：从趋势到实践

import pandas as pd
import matplotlib.pyplot as plt

# 读取交通流量数据（假设数据源自传感器）
df = pd.read_csv('traffic_data.csv')

# 统计每小时的车辆数量
df['timestamp'] = pd.to_datetime(df['timestamp'])
df.set_index('timestamp', inplace=True)
df.resample('H')['vehicle_count'].sum().plot()
plt.title("每小时车辆流量")
plt.show()

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
import pandas as pd

# 读取患者数据
df = pd.read_csv('health_data.csv')
X = df.drop(columns=['diabetes'])
y = df['diabetes']

# 训练机器学习模型
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = RandomForestClassifier()
model.fit(X_train, y_train)

# 预测并评估准确性
y_pred = model.predict(X_test)
print("预测准确率:", accuracy_score(y_test, y_pred))

from sklearn.neighbors import NearestNeighbors
import numpy as np

# 假设每个用户的购买记录为一个向量
user_item_matrix = np.array([
    [1, 0, 1, 0, 1],  # 用户1的购买记录
    [0, 1, 0, 1, 0],  # 用户2的购买记录
])

# 训练推荐模型
model = NearestNeighbors(n_neighbors=1, metric='cosine')
model.fit(user_item_matrix)

# 查询最相似的用户
distances, indices = model.kneighbors(user_item_matrix)
print("最相似的用户索引:", indices)

from sklearn.ensemble import GradientBoostingClassifier

# 假设设备传感器数据
df = pd.read_csv('machine_sensor_data.csv')
X = df.drop(columns=['failure'])
y = df['failure']

# 训练预测模型
model = GradientBoostingClassifier()
model.fit(X, y)

# 预测某设备的故障概率
failure_prob = model.predict_proba([[0.8, 0.5, 0.3]])
print("设备故障概率:", failure_prob)

from sklearn.ensemble import IsolationForest

# 生成模拟交易数据
data = np.random.rand(1000, 2)  # 1000 笔交易，每笔交易两个特征
model = IsolationForest(contamination=0.05)  # 5% 交易为异常
model.fit(data)

# 预测交易是否异常
predictions = model.predict(data)
print("异常交易数量:", sum(predictions == -1))