wgz_forecast/carbon/matrix2series.ipynb

In [63]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

In [64]:

data = pd.read_csv('./data/carbon_original.csv')
data.head()

Out[64]:

	MSN	YYYYMM	Value	Column_Order	Description	Unit
0	CLEIEUS	197301	72.076	1	Coal Electric Power Sector CO2 Emissions	Million Metric Tons of Carbon Dioxide
1	CLEIEUS	197302	64.442	1	Coal Electric Power Sector CO2 Emissions	Million Metric Tons of Carbon Dioxide
2	CLEIEUS	197303	64.084	1	Coal Electric Power Sector CO2 Emissions	Million Metric Tons of Carbon Dioxide
3	CLEIEUS	197304	60.842	1	Coal Electric Power Sector CO2 Emissions	Million Metric Tons of Carbon Dioxide
4	CLEIEUS	197305	61.798	1	Coal Electric Power Sector CO2 Emissions	Million Metric Tons of Carbon Dioxide

In [65]:

use_data = data[data['MSN']=='CLEIEUS'].iloc[:,[2]]

In [66]:

use_data

Out[66]:

	Value
0	72.076
1	64.442
2	64.084
3	60.842
4	61.798
...	...
561	72.84
562	71.41
563	82.51
564	115.772
565	135.958

566 rows × 1 columns

In [66]:

In [67]:

# 生成日期范围（484天）
dates = pd.date_range(start='2022-01-01', periods=566, freq='H')
dates=pd.DataFrame(dates, columns=['date'])

C:\Users\liuhao\AppData\Local\Temp\ipykernel_17444\217526566.py:2: FutureWarning: 'H' is deprecated and will be removed in a future version, please use 'h' instead.
  dates = pd.date_range(start='2022-01-01', periods=566, freq='H')

In [68]:

date_data=pd.concat([dates,use_data],axis=1)

In [69]:

# 将 'Value' 列转换为 float 类型
date_data['Value'] = date_data['Value'].astype(float)

In [70]:

# 绘制第二列的图像
plt.figure(figsize=(10, 6))
plt.plot(date_data.index, date_data['Value'], label='Value')
plt.xlabel('Date')
plt.ylabel('Value')
plt.title('Time Series Plot of Second Column')
plt.legend()
plt.grid(True)
plt.show()

In [71]:

date_data.to_csv('data/carbon_data_hourly.csv', index=False, encoding='utf-8-sig')

In [71]: