In [1]:

import pandas as pd

import pandas as pd

Parse CSV, trial & error¶

In [2]:

pd.read_csv('output/SchPark01.csv')

pd.read_csv('output/SchPark01.csv')

Out[2]:

	2011/01/01;00:00;0.0;-0.6
0	2011/01/01;00:15;0.0;-0.4
1	2011/01/01;00:30;0.0;-0.5
2	2011/01/01;00:45;0.0;-0.5
3	2011/01/01;01:00;0.0;-0.7
4	2011/01/01;01:15;0.0;-0.6
...	...
35034	2011/12/31;22:45;0.0;7.9
35035	2011/12/31;23:00;0.0;7.9
35036	2011/12/31;23:15;0.0;8.4
35037	2011/12/31;23:30;0.0;8.5
35038	2011/12/31;23:45;0.0;8.1

35039 rows × 1 columns

In [3]:

pd.read_csv('output/SchPark01.csv', sep=';')

pd.read_csv('output/SchPark01.csv', sep=';')

Out[3]:

	2011/01/01	00:00	0.0	-0.6
0	2011/01/01	00:15	0.0	-0.4
1	2011/01/01	00:30	0.0	-0.5
2	2011/01/01	00:45	0.0	-0.5
3	2011/01/01	01:00	0.0	-0.7
4	2011/01/01	01:15	0.0	-0.6
...	...	...	...	...
35034	2011/12/31	22:45	0.0	7.9
35035	2011/12/31	23:00	0.0	7.9
35036	2011/12/31	23:15	0.0	8.4
35037	2011/12/31	23:30	0.0	8.5
35038	2011/12/31	23:45	0.0	8.1

35039 rows × 4 columns

In [4]:

pd.read_csv('output/SchPark01.csv', sep=';',
            names = ['date', 'time', 'ghi', 'ta'])

pd.read_csv('output/SchPark01.csv', sep=';', names = ['date', 'time', 'ghi', 'ta'])

Out[4]:

	date	time	ghi	ta
0	2011/01/01	00:00	0.0	-0.6
1	2011/01/01	00:15	0.0	-0.4
2	2011/01/01	00:30	0.0	-0.5
3	2011/01/01	00:45	0.0	-0.5
4	2011/01/01	01:00	0.0	-0.7
...	...	...	...	...
35035	2011/12/31	22:45	0.0	7.9
35036	2011/12/31	23:00	0.0	7.9
35037	2011/12/31	23:15	0.0	8.4
35038	2011/12/31	23:30	0.0	8.5
35039	2011/12/31	23:45	0.0	8.1

35040 rows × 4 columns

# NOTE: This will not work because of empty values: ghi and ta will be parsed as strings pd.read_csv('output/SchPark01.csv', sep=';', names = ['date', 'time', 'ghi', 'ta']).ghi.mean()

Parse CSV¶

In [5]:

df = pd.read_csv('output/SchPark01.csv',
            sep = ';',
            na_values = ' ',
            names = ['date', 'time', 'ghi', 'ta'],
)

# https://stackoverflow.com/a/77983644/6419007
df['datetime'] = pd.to_datetime(df.pop('date')+' '+ df.pop('time'),
                                format="%Y/%m/%d %H:%M")
df = df.set_index('datetime')
df

df = pd.read_csv('output/SchPark01.csv', sep = ';', na_values = ' ', names = ['date', 'time', 'ghi', 'ta'], ) # https://stackoverflow.com/a/77983644/6419007 df['datetime'] = pd.to_datetime(df.pop('date')+' '+ df.pop('time'), format="%Y/%m/%d %H:%M") df = df.set_index('datetime') df

Out[5]:

	ghi	ta
datetime
2011-01-01 00:00:00	0.0	-0.6
2011-01-01 00:15:00	0.0	-0.4
2011-01-01 00:30:00	0.0	-0.5
2011-01-01 00:45:00	0.0	-0.5
2011-01-01 01:00:00	0.0	-0.7
...	...	...
2011-12-31 22:45:00	0.0	7.9
2011-12-31 23:00:00	0.0	7.9
2011-12-31 23:15:00	0.0	8.4
2011-12-31 23:30:00	0.0	8.5
2011-12-31 23:45:00	0.0	8.1

35040 rows × 2 columns

Plots¶

In [6]:

import matplotlib.pyplot as plt

import matplotlib.pyplot as plt

In [7]:

plt.rcParams['figure.figsize'] = (15, 8)

plt.rcParams['figure.figsize'] = (15, 8)

In [8]:

df.plot();

df.plot();

In [9]:

df.resample('ME').mean().plot();

df.resample('ME').mean().plot();

In [10]:

import seaborn as sns

import seaborn as sns

In [11]:

sns.heatmap(
        pd.pivot_table(df, values='ghi', index=df.index.time, columns=df.index.dayofyear),
        annot=False);

sns.heatmap( pd.pivot_table(df, values='ghi', index=df.index.time, columns=df.index.dayofyear), annot=False);

In [12]:

sns.heatmap(
        pd.pivot_table(df, values='ta', index=df.index.time, columns=df.index.dayofyear),
        annot=False);

sns.heatmap( pd.pivot_table(df, values='ta', index=df.index.time, columns=df.index.dayofyear), annot=False);