In [1]:

import pandas as pd

url_prefix = "https://raw.githubusercontent.com/coderefinery/data-visualization-python/main/data/"

data_tromso = pd.read_csv(url_prefix + "tromso-monthly.csv")
data_oslo = pd.read_csv(url_prefix + "oslo-monthly.csv")

data_monthly = pd.concat([data_tromso, data_oslo], axis=0)

# let us print the combined result
data_monthly

Out[1]:

	name	station	date	max temperature	precipitation	min temperature
0	Tromso - Langnes	SN90490	10.2022	10.7	187.0	-4.2
1	Tromso - Langnes	SN90490	11.2022	8.5	41.5	-7.0
2	Tromso - Langnes	SN90490	12.2022	5.6	88.8	-11.7
3	Tromso - Langnes	SN90490	1.2023	7.7	111.4	-13.9
4	Tromso - Langnes	SN90490	2.2023	6.6	171.3	-10.7
5	Tromso - Langnes	SN90490	3.2023	4.5	157.0	-15.1
6	Tromso - Langnes	SN90490	4.2023	9.8	85.0	-7.1
7	Tromso - Langnes	SN90490	5.2023	17.7	101.2	-4.6
8	Tromso - Langnes	SN90490	6.2023	25.4	43.4	-0.4
9	Tromso - Langnes	SN90490	7.2023	26.7	14.0	6.0
10	Tromso - Langnes	SN90490	8.2023	25.1	43.4	5.4
11	Tromso - Langnes	SN90490	9.2023	19.3	163.7	0.3
12	Tromso - Langnes	SN90490	10.2023	9.8	64.8	-0.6
0	Oslo - Blindern	SN18700	10.2022	17.1	82.9	-0.4
1	Oslo - Blindern	SN18700	11.2022	15.1	83.4	-2.1
2	Oslo - Blindern	SN18700	12.2022	6.5	85.5	-14.6
3	Oslo - Blindern	SN18700	1.2023	7.2	100.5	-13.4
4	Oslo - Blindern	SN18700	2.2023	10.2	46.0	-9.4
5	Oslo - Blindern	SN18700	3.2023	9.8	72.6	-12.6
6	Oslo - Blindern	SN18700	4.2023	19.8	99.7	-4.7
7	Oslo - Blindern	SN18700	5.2023	24.2	17.0	-0.8
8	Oslo - Blindern	SN18700	6.2023	31.8	39.9	4.6
9	Oslo - Blindern	SN18700	7.2023	28.4	146.9	8.6
10	Oslo - Blindern	SN18700	8.2023	24.5	259.8	9.8
11	Oslo - Blindern	SN18700	9.2023	25.1	105.8	5.3
12	Oslo - Blindern	SN18700	10.2023	17.1	7.3	-0.7

In [2]:

# replace mm.yyyy to date format
data_monthly["date"] = pd.to_datetime(list(data_monthly["date"]), format="%m.%Y")

In [3]:

# print the first 5 rows
data_monthly.head()

Out[3]:

	name	station	date	max temperature	precipitation	min temperature
0	Tromso - Langnes	SN90490	2022-10-01	10.7	187.0	-4.2
1	Tromso - Langnes	SN90490	2022-11-01	8.5	41.5	-7.0
2	Tromso - Langnes	SN90490	2022-12-01	5.6	88.8	-11.7
3	Tromso - Langnes	SN90490	2023-01-01	7.7	111.4	-13.9
4	Tromso - Langnes	SN90490	2023-02-01	6.6	171.3	-10.7

In [4]:

# print the last 5 rows
data_monthly.tail()

Out[4]:

	name	station	date	max temperature	precipitation	min temperature
8	Oslo - Blindern	SN18700	2023-06-01	31.8	39.9	4.6
9	Oslo - Blindern	SN18700	2023-07-01	28.4	146.9	8.6
10	Oslo - Blindern	SN18700	2023-08-01	24.5	259.8	9.8
11	Oslo - Blindern	SN18700	2023-09-01	25.1	105.8	5.3
12	Oslo - Blindern	SN18700	2023-10-01	17.1	7.3	-0.7

In [5]:

# print all column titles - no parentheses here
data_monthly.columns

Out[5]:

Index(['name', 'station', 'date', 'max temperature', 'precipitation',
       'min temperature'],
      dtype='object')

In [6]:

# show which data types were detected
data_monthly.dtypes

Out[6]:

name                       object
station                    object
date               datetime64[ns]
max temperature           float64
precipitation             float64
min temperature           float64
dtype: object

In [7]:

# print table dimensions - no parentheses here
data_monthly.shape

Out[7]:

(26, 6)

In [8]:

# print one column
data_monthly["max temperature"]

Out[8]:

0     10.7
1      8.5
2      5.6
3      7.7
4      6.6
5      4.5
6      9.8
7     17.7
8     25.4
9     26.7
10    25.1
11    19.3
12     9.8
0     17.1
1     15.1
2      6.5
3      7.2
4     10.2
5      9.8
6     19.8
7     24.2
8     31.8
9     28.4
10    24.5
11    25.1
12    17.1
Name: max temperature, dtype: float64

In [9]:

# get some statistics
data_monthly["max temperature"].describe()

Out[9]:

count    26.000000
mean     15.930769
std       8.345862
min       4.500000
25%       8.825000
50%      16.100000
75%      24.425000
max      31.800000
Name: max temperature, dtype: float64

In [10]:

# what was the maximum temperature?
data_monthly["max temperature"].max()

Out[10]:

np.float64(31.8)

In [11]:

# print all rows where max temperature was above 20
data_monthly[data_monthly["max temperature"] > 20.0]

Out[11]:

	name	station	date	max temperature	precipitation	min temperature
8	Tromso - Langnes	SN90490	2023-06-01	25.4	43.4	-0.4
9	Tromso - Langnes	SN90490	2023-07-01	26.7	14.0	6.0
10	Tromso - Langnes	SN90490	2023-08-01	25.1	43.4	5.4
7	Oslo - Blindern	SN18700	2023-05-01	24.2	17.0	-0.8
8	Oslo - Blindern	SN18700	2023-06-01	31.8	39.9	4.6
9	Oslo - Blindern	SN18700	2023-07-01	28.4	146.9	8.6
10	Oslo - Blindern	SN18700	2023-08-01	24.5	259.8	9.8
11	Oslo - Blindern	SN18700	2023-09-01	25.1	105.8	5.3

In [12]:

import altair as alt

In [13]:

# this is here for google colab to update altair
if not alt.__version__.startswith("5"):
    %pip install altair==5.3.0

In [14]:

alt.Chart(data_monthly).mark_bar().encode(
    x="date",
    y="precipitation",
    color="name",
)

Out[14]:

In [15]:

alt.Chart(data_monthly).mark_bar().encode(
    x="yearmonth(date):T",
    y="precipitation",
    color="name",
)

Out[15]:

In [16]:

alt.Chart(data_monthly).mark_bar().encode(
    x="yearmonth(date):T",
    y="precipitation",
    color="name",
    column="name",
)

Out[16]:

In [17]:

alt.Chart(data_monthly).mark_bar().encode(
    x="yearmonth(date):T",
    y="precipitation",
    color="name",
    xOffset="name",
)

Out[17]:

In [18]:

alt.Chart(data_monthly).mark_bar().encode(
    y="yearmonth(date):T",
    x="precipitation",
    color="name",
    yOffset="name",
)

Out[18]:

In [19]:

alt.Chart(data_monthly).mark_bar().encode(
    y="yearmonth(date):T",
    x=alt.X("precipitation").title("Precipitation (mm)"),
    color="name",
    yOffset="name",
)

Out[19]:

In [20]:

alt.Chart(data_monthly).mark_area(opacity=0.5).encode(
    x="yearmonth(date):T",
    y="max temperature",
    y2="min temperature",
    color="name",
)

Out[20]:

In [21]:

alt.Chart(data_monthly).mark_area(opacity=0.5).encode(
    x="yearmonth(date):T",
    y="max temperature",
    y2="min temperature",
    color="name",
    column="name",
)

Out[21]:

In [22]:

url_prefix = "https://raw.githubusercontent.com/coderefinery/data-visualization-python/main/data/"

data_tromso = pd.read_csv(url_prefix + "tromso-daily.csv")
data_oslo = pd.read_csv(url_prefix + "oslo-daily.csv")

data_daily = pd.concat([data_tromso, data_oslo], axis=0)

In [23]:

# replace dd.mm.yyyy to date format
data_daily["date"] = pd.to_datetime(list(data_daily["date"]), format="%d.%m.%Y")

# we are here only interested in the range december to may
data_daily = data_daily[
    (data_daily["date"] > "2022-12-01") & (data_daily["date"] < "2023-05-01")
]

In [24]:

alt.Chart(data_daily).mark_bar().encode(
    x="date",
    y="snow depth",
    column="name",
)

Out[24]:

In [25]:

alt.Chart(data_daily).mark_bar().encode(
    x="date",
    y="snow depth",
    color="max temperature",
    column="name",
)

Out[25]:

In [26]:

alt.Chart(data_daily).mark_bar().encode(
    x="date",
    y="snow depth",
    color=alt.Color("max temperature").scale(scheme="plasma"),
    column="name",
)

Out[26]:

In [27]:

alt.Chart(data_daily).mark_circle().encode(
    x="date",
    y="snow depth",
    color=alt.Color("max temperature").scale(scheme="plasma"),
    column="name",
)

Out[27]: