def explore_dataset(users, movies, ratings):
# Exploring the MovieLens Data (Users)
print(users.describe()) # User features
print(users.describe(include=[np.object])) # Categorical user features
# Create filters to slice the data
occupation_filter = alt.selection_multi(fields=["occupation"])
occupation_chart = alt.Chart().mark_bar().encode(
x="count()",
y=alt.Y("occupation:N"),
color=alt.condition(
occupation_filter,
alt.Color("occupation:N", scale=alt.Scale(scheme='category20')),
alt.value("lightgray")),
).properties(width=300, height=300, selection=occupation_filter)
# Create the chart
users_ratings = (ratings.groupby('user_id', as_index=False).agg({
'rating': ['count', 'mean']
}).flatten_cols().merge(users, on='user_id'))
# Create a chart for the count, and one for the mean.
altair_viewer.show(
alt.hconcat(filtered_hist('rating count', '# ratings / user',
occupation_filter),
filtered_hist('rating mean', 'mean user rating',
occupation_filter),
occupation_chart,
data=users_ratings))
# Exploring the MovieLens Data (Movies)
movies_ratings = get_movie_ratings(movies, ratings)
genre_filter, genre_chart = filter_and_chart()
(movies_ratings[['title', 'rating count',
'rating mean']].sort_values('rating count',
ascending=False).head(10))
(movies_ratings[['title', 'rating count', 'rating mean']].mask(
'rating count',
lambda x: x > 20).sort_values('rating mean', ascending=False).head(10))
# Display the number of ratings and average rating per movie
altair_viewer.show(
alt.hconcat(filtered_hist('rating count', '# ratings / movie',
genre_filter),
filtered_hist('rating mean', 'mean movie rating',
genre_filter),
genre_chart,
data=movies_ratings))
def movie_embedding_norm(models):
"""Visualizes the norm and number of ratings of the movie embeddings.
Args:
model: A MFModel object.
"""
if not isinstance(models, list):
models = [models]
df = pd.DataFrame({
'title': movies['title'],
'genre': movies['genre'],
'num_ratings': movies_ratings['rating count'],
})
charts = []
brush = alt.selection_interval()
for i, model in enumerate(models):
norm_key = 'norm' + str(i)
df[norm_key] = np.linalg.norm(model.embeddings["movie_id"], axis=1)
nearest = alt.selection(
type='single', encodings=['x', 'y'], on='mouseover', nearest=True,
empty='none')
base = alt.Chart().mark_circle().encode(
x='num_ratings',
y=norm_key,
color=alt.condition(brush, alt.value('#4c78a8'), alt.value('lightgray'))
).properties(
selection=nearest).add_selection(brush)
text = alt.Chart().mark_text(align='center', dx=5, dy=-5).encode(
x='num_ratings', y=norm_key,
text=alt.condition(nearest, 'title', alt.value('')))
charts.append(alt.layer(base, text))
return altair_viewer.show(alt.hconcat(*charts, data=df))
def bias_line_chart(data3):
"""
docstring
"""
Chart3 = alt.Chart(data3).mark_line().encode(
x='variance',
y='bias_squared'
).interactive()
return altair_viewer.show(Chart3)
def test_bar(data):
"""
A test bar chart
"""
Chart = alt.Chart(data).mark_bar().encode(
x='x',
y='y',
).interactive()
return altair_viewer.show(Chart)
def basic_bar(data2):
"""
for a basic chart, convert data to a dataframe or other accepted data sources
"""
Chart2 = alt.Chart(data2).mark_bar().encode(
x='movies',
y='num_oscars',
color='movies',
).interactive()
return altair_viewer.show(Chart2)
def bar_chart(data2):
"""
A bar chart, like the one above but with small custom alterations title and size
"""
Chart2 = alt.Chart(data2).mark_bar().encode(
alt.X ('movies', title="My Favorite Movies"),
alt.Y ('num_oscars', title="# of Academy Awards"),
color='movies',
).properties(width=200).interactive()
return altair_viewer.show(Chart2)
def visualize_movie_embeddings(data, x, y):
nearest = alt.selection(
type='single', encodings=['x', 'y'], on='mouseover', nearest=True,
empty='none')
base = alt.Chart().mark_circle().encode(
x=x,
y=y,
color=alt.condition(genre_filter, "genre", alt.value("whitesmoke")),
).properties(
width=600,
height=600,
selection=nearest)
text = alt.Chart().mark_text(align='left', dx=5, dy=-5).encode(
x=x,
y=y,
text=alt.condition(nearest, 'title', alt.value('')))
return altair_viewer.show(alt.hconcat(alt.layer(base, text), genre_chart, data=data))
def av(chart):
print(chart.to_json())
altview.show(chart)
"""
base = alt.Chart().mark_bar().encode(x=alt.X(field, bin=alt.Bin(maxbins=10), title=label),
y="count()", ).properties(width=300, )
return alt.layer(
base.transform_filter(filter),
base.encode(color=alt.value('lightgray'), opacity=alt.value(.7)), ).resolve_scale(y='independent')
# Create the chart
users_ratings = (
ratings.groupby('user_id', as_index=False).agg({'rating': ['count', 'mean']}).flatten_cols().merge(users,
on='user_id'))
# Create a chart for the count, and one for the mean.
altair_viewer.show(
alt.hconcat(filtered_hist('rating count', '# ratings / user', occupation_filter),
filtered_hist('rating mean', 'mean user rating', occupation_filter), occupation_chart,
data=users_ratings))
# Exploring the MovieLens Data (Movies)
movies_ratings = movies.merge(
ratings.groupby('movie_id', as_index=False).agg({'rating': ['count', 'mean']}).flatten_cols(), on='movie_id')
genre_filter = alt.selection_multi(fields=['genre'])
genre_chart = alt.Chart().mark_bar().encode(x="count()", y=alt.Y('genre'), color=alt.condition(
genre_filter, alt.Color("genre:N"), alt.value('lightgray'))).properties(height=300, selection=genre_filter)
(movies_ratings[['title', 'rating count', 'rating mean']]
.sort_values('rating count', ascending=False)
.head(10))
(movies_ratings[['title', 'rating count', 'rating mean']]
cornerRadiusTopLeft=3, cornerRadiusTopRight=3).encode(
x='category:N',
y=alt.Y('sum(positive_comments):Q',
title='Sum of Positive comments',
axis=alt.Axis(labelOverlap=True)),
color='category:N').properties(
title='Distribution of Positive Comments', width=300)
chart2 = alt.Chart(df).mark_bar(
cornerRadiusTopLeft=3, cornerRadiusTopRight=3).encode(
x='category:N',
y=alt.Y('sum(negative_comments):Q',
title='Sum of Negative comments',
axis=alt.Axis(labelOverlap=True)),
color='category:N').properties(
title='Distribution of Negative Comments', width=300)
chart3 = alt.Chart(df).mark_bar(
cornerRadiusTopLeft=3, cornerRadiusTopRight=3).encode(
x='category:N',
y=alt.Y('sum(neutral_comments):Q',
title='Sum of Neutral comments',
axis=alt.Axis(labelOverlap=True)),
color='category:N').properties(
title='Distribution of Neutral Comments', width=300)
concat = alt.hconcat(chart1, chart2,
chart3).resolve_scale(y='shared').configure_title(
fontSize=15, offset=5, orient='top', anchor='middle')
viewer.show(concat)
def open_chart_in_browser(chart: alt.Chart) -> NoReturnType:
# a helpful wrapper around altair_viewer.altview
altview.show(chart)
def plot_both(county='Alle_Fylker',
periodicity='day',
start=None,
end=None,
plot_lib='Altair',
view_plot=False,
plot_title=False,
width=800,
height=500):
"""
Function to generate a line-plot for Covid19's total daily cases from
FHI/Norway.
Parameters:
~~~~~~~~~~~~~~~~~~~~
:param county: str: Name od the county to be analyzed, which could
be 'Agder', 'Innlandet', 'More_og_Romsdal',
'Nordland', 'Oslo', 'Rogaland',
'Troms_og_Finnmark', Trondelag',
'Vestfold_og_Telemark', 'Vestland',
'Viken'or 'Alle_Fylker' for all counties.
:param periodicity: str: Periodicity to display the plot, which could
be 'day' or 'week'. Default 'day'.
:param start: str or date object: The starting date for the analysis.
:param end: str or date object: The ending date for the analysis.
:param plot_lib: str: The name of the plotting library to be used.
Default is 'Altair' which uses Altair. A option
is 'plt' which uses matplotlib.
:param view_plot: bool: The default is False to not show the plot.
:param plot_title: bool: The default is False to not display the
plot's title.
:param width: int: Only used for 'Altair' plot. Define the width of
the plotting. Default is 800.
:param height: int: Only used for 'Altair' plot. Define the height of
the plotting. Default is 500.
Notes:
~~~~~~~~~~~~~~~~~~~~
- If start and end are None, them it will plot the entire data-base.
"""
# creating Matplotlib or Seaborn plot
if plot_lib == 'plt':
# plotting cumulative cases
plot_cumulative_cases(county=county,
start=start,
end=end,
plot_lib=plot_lib,
view_plot=False,
plot_title=False)
# setting plots together but with independent y-axis
plt.twinx()
# plotting daily reported cases
plot_reported_cases(county=county,
start=start,
end=end,
plot_lib=plot_lib,
view_plot=False,
plot_title=False)
# setting plot's title
if plot_title is True:
plt.title(f'Data Vs (cumulative and daily cases) ' f'for {county}')
# viewing plot
if view_plot is True:
plt.show()
elif plot_lib == 'Altair':
# setting fixed parameters
col1 = 'Kumulativt antall'
title1 = 'Cumulative nrs.'
col2 = 'Nye tilfeller'
title2 = 'New report nrs.'
# setting prefix and suffix for the data-files
path = 'data/'
if periodicity == 'day':
prefix = path + 'antall-meldte-covid-19-t_day_'
elif periodicity == 'week':
prefix = path + 'antall-meldte-covid-19-t_week_'
else:
raise ValueError("Error: The given periodicity is not valid.")
suffix = '.csv'
# reading data as DataFrame
df = pd.read_csv(filepath_or_buffer=prefix + county + suffix,
sep=',',
index_col='Dato',
infer_datetime_format=True)
# setting data range
df = df[start:end]
# fixing datetime for Altair
df.reset_index(inplace=True)
base = None
if periodicity == 'day':
df['Dato'] = pd.to_datetime(df["Dato"], dayfirst=True)
# creating base for Altair plot as a function of daily-dates
base = alt.Chart(df).encode(
alt.X('Dato:T',
axis=alt.Axis(format='%Y-%m-%d'),
scale=alt.Scale(zero=False)))
if periodicity == 'week':
# creating base for Altair plot as a function of weekly-dates
base = alt.Chart(df).encode(
alt.X('Dato', scale=alt.Scale(zero=False)))
# drawing bars
bar = base.mark_bar(opacity=0.3).encode(y=alt.Y(col2,
axis=alt.Axis(
title=title2,
orient='left')), )
# drawing line
line = base.mark_line(color='red').encode(y=alt.Y(
col1, axis=alt.Axis(title=title1, orient='right')), )
# creating x-axis selections
nearest = alt.selection(type='single',
nearest=True,
on='mouseover',
fields=['Dato'],
empty='none')
# Transparent selectors across the chart. This is what tells us
# the x-value of the cursor
selectors = alt.Chart(df).mark_point().encode(
x='Dato',
opacity=alt.value(0),
).add_selection(nearest)
# drawing points on the line, and highlight based on selection
points = line.mark_point().encode(
opacity=alt.condition(nearest, alt.value(1), alt.value(0)))
# drawing a rule at the location of the selection
rules = alt.Chart(df).mark_rule(color='gray').encode(
x='Dato', ).transform_filter(nearest)
# setting dual-axis
chart = alt.layer(line, bar, selectors, points,
rules).resolve_scale(y='independent')
# setting properties and interactiveness
chart = chart.properties(
width=width, height=height,
title=f'Covid19 reports for {county}').interactive()
# adding tooltips
chart = chart.encode(tooltip=[
alt.Tooltip('Dato', title='Date'),
alt.Tooltip(col1, title=title1),
alt.Tooltip(col2, title=title2)
])
# viewing the plot
if view_plot is True:
altair_viewer.show(chart)
# altair_viewer.display(chart)
return chart
else:
raise ValueError(f"Error: Plot type {plot_lib} not implemented.")