#!/usr/bin/env python
# coding: utf-8

# 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


# 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()


# In[4]:


# print the last 5 rows
data_monthly.tail()


# In[5]:


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


# In[6]:


# show which data types were detected
data_monthly.dtypes


# In[7]:


# print table dimensions - no parentheses here
data_monthly.shape


# In[8]:


# print one column
data_monthly["max temperature"]


# In[9]:


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


# In[10]:


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


# In[11]:


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


# In[12]:


import altair as alt


# In[13]:


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


# In[14]:


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


# In[15]:


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


# In[16]:


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


# In[17]:


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


# In[18]:


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


# In[19]:


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


# In[20]:


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


# 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",
)


# 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",
)


# In[25]:


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


# In[26]:


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


# In[27]:


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