不同子时段作物含水量时间序列趋势计算及可视化需求

以下提供R和Python两种实现方式，完成指定时段的趋势计算与可视化：

R实现 #

1. 数据准备与时段划分 #

# 加载依赖包
library(lubridate)
library(ggplot2)

# 创建数据集
dates <- seq(as.Date("2016-09-01"), as.Date("2020-07-30"), by=15)
water <- c(0.5702722, 0.5631781, 0.5560839, 0.5555985, 0.5519783, 0.5463459, 
           0.5511598, 0.546652, 0.5361545, 0.530012, 0.5360571, 0.5396569, 
           0.5683526, 0.6031535, 0.6417821, 0.671358, 0.7015542, 0.7177007, 
           0.7103561, 0.7036985, 0.6958607, 0.6775161, 0.6545367, 0.6380155, 
           0.6113306, 0.5846186, 0.5561815, 0.5251135, 0.5085149, 0.495352, 
           0.485819, 0.4730029, 0.4686458, 0.4616468, 0.4613918, 0.4615532, 
           0.4827496, 0.5149105, 0.5447824, 0.5776764, 0.6090217, 0.6297454, 
           0.6399422, 0.6428941, 0.6586344, 0.6507473, 0.6290631, 0.6011123, 
           0.5744375, 0.5313527, 0.5008027, 0.4770338, 0.4564025, 0.4464508, 
           0.4309046, 0.4351668, 0.4490393, 0.4701232, 0.4911582, 0.5162941, 
           0.5490387, 0.5737573, 0.6031149, 0.6400073, 0.6770058, 0.7048311, 
           0.7255012, 0.739107, 0.7338938, 0.7265202, 0.6940718, 0.6757214, 
           0.6460862, 0.6163091, 0.5743775, 0.5450822, 0.5057753, 0.4715266, 
           0.4469859, 0.4303232, 0.4187793, 0.4119401, 0.4201316, 0.426369, 
           0.4419331, 0.4757525, 0.5070846, 0.5248457, 0.5607567, 0.5859825, 
           0.6107531, 0.6201754, 0.6356589, 0.6336177, 0.6275579, 0.6214981)

df <- data.frame(date = dates, water_content = water)

# 划分目标时段
period1 <- df[df$date >= as.Date("2016-09-01") & df$date <= as.Date("2019-11-30"), ]
period2 <- df[df$date >= as.Date("2019-12-15") & df$date <= as.Date("2020-07-30"), ]

2. 计算线性趋势 #

# 时段1趋势回归
model1 <- lm(water_content ~ as.numeric(date), data = period1)
trend1 <- coef(model1)
cat("时段1（2016-09-01至2019-11-30）趋势：\n")
cat(paste0("斜率：", round(trend1[2], 8), "，截距：", round(trend1[1], 4), "\n"))

# 时段2趋势回归
model2 <- lm(water_content ~ as.numeric(date), data = period2)
trend2 <- coef(model2)
cat("时段2（2019-12-15至2020-07-30）趋势：\n")
cat(paste0("斜率：", round(trend2[2], 8), "，截距：", round(trend2[1], 4), "\n"))

3. 可视化绘制 #

ggplot(df, aes(x = date, y = water_content)) +
  geom_point(color = "darkblue", size = 1.5) +
  # 时段1趋势线
  geom_smooth(data = period1, method = "lm", se = FALSE, color = "red", linetype = "solid") +
  # 时段2趋势线
  geom_smooth(data = period2, method = "lm", se = FALSE, color = "green", linetype = "solid") +
  # 时段分割虚线
  geom_vline(xintercept = as.Date("2019-11-30"), linetype = "dashed", color = "gray") +
  # 趋势标注
  annotate("text", x = as.Date("2018-03-01"), y = max(df$water_content)*0.95, 
           label = paste0("时段1趋势：斜率=", round(trend1[2], 8)), color = "red") +
  annotate("text", x = as.Date("2020-02-01"), y = max(df$water_content)*0.9, 
           label = paste0("时段2趋势：斜率=", round(trend2[2], 8)), color = "green") +
  labs(title = "作物含水量时间序列及分时段趋势", x = "日期", y = "作物含水量") +
  theme_minimal()

Python实现 #

1. 数据准备与时段划分 #

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression

# 创建数据集
dates = pd.date_range(start="2016-09-01", end="2020-07-30", freq="15D")
water = np.array([0.5702722, 0.5631781, 0.5560839, 0.5555985, 0.5519783, 0.5463459, 
                  0.5511598, 0.546652, 0.5361545, 0.530012, 0.5360571, 0.5396569, 
                  0.5683526, 0.6031535, 0.6417821, 0.671358, 0.7015542, 0.7177007, 
                  0.7103561, 0.7036985, 0.6958607, 0.6775161, 0.6545367, 0.6380155, 
                  0.6113306, 0.5846186, 0.5561815, 0.5251135, 0.5085149, 0.495352, 
                  0.485819, 0.4730029, 0.4686458, 0.4616468, 0.4613918, 0.4615532, 
                  0.4827496, 0.5149105, 0.5447824, 0.5776764, 0.6090217, 0.6297454, 
                  0.6399422, 0.6428941, 0.6586344, 0.6507473, 0.6290631, 0.6011123, 
                  0.5744375, 0.5313527, 0.5008027, 0.4770338, 0.4564025, 0.4464508, 
                  0.4309046, 0.4351668, 0.4490393, 0.4701232, 0.4911582, 0.5162941, 
                  0.5490387, 0.5737573, 0.6031149, 0.6400073, 0.6770058, 0.7048311, 
                  0.7255012, 0.739107, 0.7338938, 0.7265202, 0.6940718, 0.6757214, 
                  0.6460862, 0.6163091, 0.5743775, 0.5450822, 0.5057753, 0.4715266, 
                  0.4469859, 0.4303232, 0.4187793, 0.4119401, 0.4201316, 0.426369, 
                  0.4419331, 0.4757525, 0.5070846, 0.5248457, 0.5607567, 0.5859825, 
                  0.6107531, 0.6201754, 0.6356589, 0.6336177, 0.6275579, 0.6214981])

df = pd.DataFrame({"date": dates, "water_content": water})

# 划分目标时段
period1 = df[(df["date"] >= "2016-09-01") & (df["date"] <= "2019-11-30")]
period2 = df[(df["date"] >= "2019-12-15") & (df["date"] <= "2020-07-30")]

2. 计算线性趋势 #

# 日期转数值（自时段起始日的天数）
def date_to_num(df):
    return (df["date"] - df["date"].min()).dt.days.values.reshape(-1, 1)

# 时段1趋势计算
X1 = date_to_num(period1)
y1 = period1["water_content"].values
model1 = LinearRegression().fit(X1, y1)
print(f"时段1（2016-09-01至2019-11-30）趋势：")
print(f"斜率：{model1.coef_[0]:.8f}，截距：{model1.intercept_:.4f}")

# 时段2趋势计算
X2 = date_to_num(period2)
y2 = period2["water_content"].values
model2 = LinearRegression().fit(X2, y2)
print(f"时段2（2019-12-15至2020-07-30）趋势：")
print(f"斜率：{model2.coef_[0]:.8f}，截距：{model2.intercept_:.4f}")

3. 可视化绘制 #

plt.figure(figsize=(12, 6))

# 绘制原始观测点
plt.scatter(df["date"], df["water_content"], color="darkblue", s=20, label="观测值")

# 绘制时段1趋势线
plt.plot(period1["date"], model1.predict(X1), color="red", linestyle="-", 
         label=f"时段1趋势（斜率={model1.coef_[0]:.8f}）")

# 绘制时段2趋势线
plt.plot(period2["date"], model2.predict(X2), color="green", linestyle="-", 
         label=f"时段2趋势（斜率={model2.coef_[0]:.8f}）")

# 添加时段分割线
plt.axvline(pd.to_datetime("2019-11-30"), color="gray", linestyle="--", label="时段分割")

plt.title("作物含水量时间序列及分时段趋势", fontsize=14)
plt.xlabel("日期", fontsize=12)
plt.ylabel("作物含水量", fontsize=12)
plt.legend()
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

内容的提问来源于stack exchange，提问作者kl40