Python 3.x 条形图的分组和重采样：

我有一个数据框，它记录了不同年份中几个不同位置的浓度，具有很高的时间频率（基本上，你的错误来自于这个不明确的索引，你传递的是一列连续的浮点值，用于按行选择索引，目前是日期时间类型

df_new[df_new['value']]           # INDEXING DATETIME USING FLOAT VALUES
...
df_month[df_month['value']]       # COLUMN value DOES NOT EXIST

您可能打算在重采样期间选择列值（从其他列中选择）

Unnamed: 0 location  value  \
date                                    location          value                                                                         
2017-10-21 08:45:00+05:30        8335    M                339.3   
2017-08-18 17:45:00+05:30        8344    M                 45.1   
2017-11-08 13:15:00+05:30        8347    L                594.4   
2017-10-21 13:15:00+05:30        8659    N                189.9   
2017-08-18 15:45:00+05:30        8662    N                 46.5   

diurnal = df_new['value'].resample('12h')

diurnal.mean()[diurnal.count() >= 9]

daily_mean = diurnal_mean.resample('d').mean()    
df_month = daily_mean.resample('m').mean()       # REMOVE value BEING UNDERLYING SERIES
df_yearly = df_month.resample('y')                

但是，上面没有任何位置可以保留打印位置。因此，使用

groupby（pd.Grouper（…）

---

用随机、可复制的数据证明：

数据

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns

np.random.seed(242020)
random_df = pd.DataFrame({'date': (np.random.choice(pd.date_range('2017-01-01', '2019-12-31'), 5000) + 
                                   pd.to_timedelta(np.random.randint(60*60, 60*60*24, 5000), unit='s')),
                          'location': np.random.choice(list("KLM"), 5000),
                          'value': np.random.uniform(10, 1000, 5000)                          
                         })

聚合

loc_list = list("KLM")

# NEW DATA FRAME WITH DATA FILTERING
df = (random_df.set_index(random_df['date'])
               .assign(Year = lambda x: x['date'].dt.year,
                       location = lambda x: x['location'].where(x["location"] != "mm", "M"))
               .query('(location == @loc_list) and (value >= 2 and value <= 400)')
      )

# 12h AGGREGATION
diurnal = (df_new.groupby(["location", pd.Grouper(freq='12h')])["value"]
                 .agg(["count", "mean"])
                 .reset_index().set_index(['date'])
                 .query("count >= 2")
          )


# d, m, y AGGREGATION
daily_mean = diurnal.groupby(["location", pd.Grouper(freq='d')])["mean"].mean()
df_month = diurnal.groupby(["location", pd.Grouper(freq='m')])["mean"].mean()
df_yearly = (diurnal.groupby(["location", pd.Grouper(freq='y')])["mean"].mean()
                    .reset_index()
                    .assign(Year = lambda x: x["date"].dt.year)
            )

print(df_yearly)
#   location       date        mean  Year
# 0        K 2017-12-31  188.984592  2017
# 1        K 2018-12-31  199.521702  2018
# 2        K 2019-12-31  216.497268  2019
# 3        L 2017-12-31  214.347873  2017
# 4        L 2018-12-31  199.232711  2018
# 5        L 2019-12-31  177.689221  2019
# 6        M 2017-12-31  222.412711  2017
# 7        M 2018-12-31  241.597977  2018
# 8        M 2019-12-31  215.554228  2019

---

请发布a的

df

数据，然后理想地显示所需的结果。这是

df

之前还是之后？作为测试，请尝试完全运行您发布的内容（数据+代码）在空的Python环境中，确保它复制错误或不希望的结果。这是一个虚拟数据帧，显示了我要绘制的内容；值列理想情况下应该包括最终重采样的质量控制浓度。

# AGGREGATE TO KEEP LOCATION AND 12h
diurnal = (df_new.groupby(["location", pd.Grouper(freq='12h')])["value"]
                 .agg(["count", "mean"])
                 .reset_index().set_index(['date'])
           )
# FILTER
diurnal_sub = diurnal[diurnal["count"] >= 9]

# MULTIPLE DATE TIME LEVEL MEANS
daily_mean = diurnal_sub.groupby(["location", pd.Grouper(freq='d')])["mean"].mean()
df_month = diurnal_sub.groupby(["location", pd.Grouper(freq='m')])["mean"].mean()
df_yearly = diurnal_sub.groupby(["location", pd.Grouper(freq='y')])["mean"].mean()

print(df_yearly)

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns

np.random.seed(242020)
random_df = pd.DataFrame({'date': (np.random.choice(pd.date_range('2017-01-01', '2019-12-31'), 5000) + 
                                   pd.to_timedelta(np.random.randint(60*60, 60*60*24, 5000), unit='s')),
                          'location': np.random.choice(list("KLM"), 5000),
                          'value': np.random.uniform(10, 1000, 5000)                          
                         })

loc_list = list("KLM")

# NEW DATA FRAME WITH DATA FILTERING
df = (random_df.set_index(random_df['date'])
               .assign(Year = lambda x: x['date'].dt.year,
                       location = lambda x: x['location'].where(x["location"] != "mm", "M"))
               .query('(location == @loc_list) and (value >= 2 and value <= 400)')
      )

# 12h AGGREGATION
diurnal = (df_new.groupby(["location", pd.Grouper(freq='12h')])["value"]
                 .agg(["count", "mean"])
                 .reset_index().set_index(['date'])
                 .query("count >= 2")
          )


# d, m, y AGGREGATION
daily_mean = diurnal.groupby(["location", pd.Grouper(freq='d')])["mean"].mean()
df_month = diurnal.groupby(["location", pd.Grouper(freq='m')])["mean"].mean()
df_yearly = (diurnal.groupby(["location", pd.Grouper(freq='y')])["mean"].mean()
                    .reset_index()
                    .assign(Year = lambda x: x["date"].dt.year)
            )

print(df_yearly)
#   location       date        mean  Year
# 0        K 2017-12-31  188.984592  2017
# 1        K 2018-12-31  199.521702  2018
# 2        K 2019-12-31  216.497268  2019
# 3        L 2017-12-31  214.347873  2017
# 4        L 2018-12-31  199.232711  2018
# 5        L 2019-12-31  177.689221  2019
# 6        M 2017-12-31  222.412711  2017
# 7        M 2018-12-31  241.597977  2018
# 8        M 2019-12-31  215.554228  2019

sns.set()
fig, axs = plt.subplots(figsize=(12,5))
sns.barplot(x='location', y='mean', hue='Year', data= df_yearly, ax=axs)

plt.title("Location Value Yearly Aggregation", weight="bold", size=16)
plt.show()
plt.clf()
plt.close()