def createChart(data, zipcode):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
#rating_selection = alt.selection_single(name="rating", empty="all", encodings=['y'])
data = data[data['zipcode'] == zipcode].nlargest(20, 'num')
try:
maxCount = int(data['num'].max())
except ValueError:
maxCount = 10
data = pd.DataFrame([{"name": "undefine", "num": 0}])
return alt.Chart(data)\
.mark_bar(stroke="Black")\
.encode(
alt.X("num:Q", axis=alt.Axis(title="Restaurants"),
scale=alt.Scale(domain=(0,maxCount))),
alt.Y('name:O', axis=alt.Axis(title="cuisine"),
sort=alt.SortField(field="num", op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection,
)
def createChart(data, name=''):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
barMean = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("rating:Q", axis=alt.Axis(title="The number of restaurants")),
alt.Y('name:O', axis=alt.Axis(title="Cuisines".format(name)),
sort=alt.SortField(field="rating", op="mean", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection,
)
return alt.hconcat(
barMean,
data=data,
title="The number of restaurants ({} in NYC) - Top 25 cuisines".format(
name))
def createChart(data, zipcode):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
try:
data = pd.concat([data['cuisine'], data['perZip' + zipcode]],
axis=1).nlargest(20, 'perZip' + zipcode)
maxCount = int(data['perZip' + zipcode].max())
except KeyError:
maxCount = 1
data = pd.DataFrame([{"cuisine": "", 'perZip' + zipcode: 0}])
return alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X('perZip'+zipcode+':Q', axis=alt.Axis(title="Restaurants"),
scale=alt.Scale(domain=(0,maxCount))),
alt.Y('cuisine:O', axis=alt.Axis(title="cuisine"),
sort=alt.SortField(field='perZip'+zipcode, op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection,
)
def draw_chart(data, zipcode):
# color expression, highlights bar on mouseover
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression, "SteelBlue")
#highlight bar when mouse is hovering
highlight_selection = alt.selection_single(name="highlight", empty="all", on="mouseover")
try:
data = pd.concat([data["cuisine"], data["perZip"+zipcode]], axis=1).nlargest(25, "perZip"+zipcode)
maxCount = int(data["perZip"+zipcode].max())
except KeyError:
maxCount = 1
data = pd.DataFrame([{"cuisine":"", "perZip"+zipcode:0}])
return alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X("perZip"+zipcode+":Q",
axis=alt.Axis(title="Number of Restaurants"),
scale=alt.Scale(domain=(0,maxCount))),
alt.Y("cuisine:O", axis=alt.Axis(title="Cuisine Type"),
sort=alt.SortField(field="perZip"+zipcode,
op="argmax")),
alt.ColorValue("LightGrey",
condition=color_condition),
).properties(
selection = highlight_selection,
)
def plotWords(dfWords):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression, "SteelBlue")
highlight_selection = alt.selection_single(name="highlight", empty="all", on="mouseover")
return alt.Chart(dfWords) \
.mark_bar(stroke="Black") \
.encode(
alt.X("freq", axis=alt.Axis(title="Count")),
alt.Y('word:O', axis=alt.Axis(title="Keyword"),
sort=alt.SortField(field="freq", op="max", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection
)
def showRatingDistribution(df, name=''):
zips = name
try:
data = df.sort_values(by=zips, ascending=False).head(15)
except KeyError:
return alt.Chart(pd.DataFrame()).mark_bar()
else:
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(
color_expression, "SteelBlue")
## There are two types of selection in our chart:
## (1) A selection for highlighting a bar when the mouse is hovering over
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
## (2) A selection for updating the rating distribution when the mouse is clicked
## Note the encodings=['y'] parameter is needed to specify that once a selection
## is triggered, it will propagate the encoding channel 'y' as a condition for
## any subsequent filter done on this selection. In short, it means use the data
## field associated with the 'y' axis as a potential filter condition.
# rating_selection = alt.selection_single(name="rating", empty="all", encodings=['y'])
## We need to compute the max count to scale our distribution appropriately
# maxCount = int(data[zips].max())
## Our visualization consists of two bar charts placed side by side. The first one
## sorts the apps by their average ratings as below. Note the compound selection
## that is constructed by adding the two selections together.
barMean = alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X(zips+":Q", axis=alt.Axis(title="Restuarants")),
alt.Y('cuisine:O', axis=alt.Axis(title="Cuisine".format(name)),
sort=alt.SortField(field=zips, op="max", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection
)
return barMean
def createChart(data, zip):
color_expression = "(highlight._vgsid_==datum._vgsid_)"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
on="mouseover",
empty="none")
vis2 = alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X("total:Q", axis=alt.Axis(title="Restaurants")),
alt.Y('cuisine:O', sort=alt.SortField(field="total", op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection=(highlight_selection),
)
return vis2
def createChart(data, name):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
rating_selection = alt.selection_single(name="rating",
empty="all",
encodings=['y'])
maxCount = int(data['rating'].value_counts().max())
barMean = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("mean(rating):Q", axis=alt.Axis(title="Rating")),
alt.Y('name:O', axis=alt.Axis(title="{} App Name".format(name)),
sort=alt.SortField(field="rating", op="mean", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection+rating_selection,
)
barRating = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("rating:O", axis=alt.Axis(title="Rating"),
scale=alt.Scale(type='band', domain=list(range(1,6))),
),
alt.Y("count()", axis=alt.Axis(title="Number of Ratings"),
scale=alt.Scale(domain=(0,maxCount)),
),
).properties(
selection = highlight_selection,
).transform_filter(
rating_selection.ref()
)
return alt.hconcat(barMean,
barRating,
data=data,
title="{} App Ratings".format(name))
def createChart(data, zip):
color_expression = "(indexof(lower(datum.cuisine), search.term)>=0) || (highlight._vgsid_==datum._vgsid_)"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
on="mouseover",
empty="none")
search_selection = alt.selection_single(name="search",
on="mouseover",
empty="none",
fields=["term"],
bind=alt.VgGenericBinding('input'))
vis2 = alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X("total:Q", axis=alt.Axis(title="Restaurants")),
alt.Y('cuisine:O', sort=alt.SortField(field="total", op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection=(highlight_selection + search_selection),
)
return vis2
def showRatingDistribution(data, name=''):
"""Create an interaactive visualization showing the distribution of ratings
Args:
data (DataFrame): the input data frame that must at least consists
two columns 'name' and 'rating' for app names and ratings.
name (str): the name of the platform (optional) to be displayed.
Return:
Chart: an Altair chart object that corresponds to the visualization
"""
## The color expression for highlighting the bar under mouse
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
## There are two types of selection in our chart:
## (1) A selection for highlighting a bar when the mouse is hovering over
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
## (2) A selection for updating the rating distribution when the mouse is clicked
## Note the encodings=['y'] parameter is needed to specify that once a selection
## is triggered, it will propagate the encoding channel 'y' as a condition for
## any subsequent filter done on this selection. In short, it means use the data
## field associated with the 'y' axis as a potential filter condition.
rating_selection = alt.selection_single(name="PROVIDER",
empty="all",
encodings=['y'])
## We need to compute the max count to scale our distribution appropriately
maxCount_BORO = int(data['BORO'].value_counts().max())
maxCount_SSID = int(data['PROVIDER'].value_counts().max())
## Our visualization consists of two bar charts placed side by side. The first one
## sorts the apps by their average ratings as below. Note the compound selection
## that is constructed by adding the two selections together.
barMean = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.Y('BORO:O', axis=alt.Axis(title="Location of Hotspot"),
sort=alt.SortField(field="BORO", op="count", order='descending'),
),
alt.X("count()", axis=alt.Axis(title="Number of Hotspot"),
scale = alt.Scale(domain=(0,maxCount_BORO)),
),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection+rating_selection
)
## The second one uses the selected app specified by the rating_selection
## to filter the data, and build a histogram based on the ratings. Note
## the use of rating_selection.ref() as a condition for transform_filter().
## The scale was explicitly constructed for the X axis to fill out the
## the potential empty values, e.g. no one gave an app a score of 3, but
## we still want to show 1, 2, 3, 4, and 5 in the axis (but not in with .5).
barRating = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("PROVIDER:O", axis=alt.Axis(title="PROVIDER"),
sort=alt.SortField(field="PROVIDER", op="count", order='descending'),
),
alt.Y("count()", axis=alt.Axis(title="Number of Hotspot"),
scale=alt.Scale(domain=(0,maxCount_SSID)),
),
alt.ColorValue("LightGrey"),
).properties(
selection = highlight_selection
).transform_filter(
rating_selection.ref()
)
states = "https://raw.githubusercontent.com/hvo/datasets/master/nyc_zip.geojson"
# US states background
background = alt.Chart(states).mark_geoshape(
fill='lightgray',
stroke='white').properties(title='Map', width=500,
height=500).project('albersUsa')
points = alt.Chart(data).mark_point(filled=True, size=200).encode(
longitude='LON:Q',
latitude='LAT:Q',
color=alt.value('SteelBlue'),
size=alt.value(30)).transform_filter(rating_selection.ref())
## We just need to concatenate the plots horizontally, and return the result.
return alt.hconcat(alt.vconcat(
barMean,
barRating,
data=data,
title="{} Hotspot Distribution".format(name)), (background + points),
data=data)
def showRatingDistribution(data, name=''):
"""Create an interactive visualization showing the distribution of ratings
Args:
data (DataFrame): the input data frame that must at least consists
two columns 'name' and 'rating' for app names and ratings.
name (str): the name of the platform (optional) to be displayed.
Return:
Chart: an Altair chart object that corresponds to the visualization
"""
# The color expression for highlighting the bar under mouse
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
# There are two types of selection in our chart:
# (1) A selection for highlighting a bar when the mouse is hovering over
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
# (2) A selection for updating the rating distribution when the mouse is clicked
# Note the encodings=['y'] parameter is needed to specify that once a selection
# is triggered, it will propagate the encoding channel 'y' as a condition for
# any subsequent filter done on this selection. In short, it means use the data
# field associated with the 'y' axis as a potential filter condition.
rating_selection = alt.selection_single(name="rating",
empty="all",
encodings=['y'])
# We need to compute the max count to scale our distribution appropriately
maxCount = int(data['rating'].value_counts().max())
# Our visualization consists of two bar charts placed side by side. The first one
# sorts the apps by their average ratings as below. Note the compound selection
# that is constructed by adding the two selections together.
barMean = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("mean(rating):Q", axis=alt.Axis(
title="Average Rating", tickCount=min(maxCount, 6))),
alt.Y('name:O', axis=alt.Axis(title="{} App Name".format(name)),
sort=alt.EncodingSortField(field="rating", op="mean", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
) \
.add_selection(highlight_selection) \
.add_selection(rating_selection)
# The second one uses the selected app specified by the rating_selection
# to filter the data, and build a histogram based on the ratings. Note
# the use of rating_selection.ref() as a condition for transform_filter().
# The scale was explicitly constructed for the X axis to fill out the
# the potential empty values, e.g. no one gave an app a score of 3, but
# we still want to show 1, 2, 3, 4, and 5 in the axis (but not in with .5).
barRating = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("rating:O", axis=alt.Axis(title="Rating"),
scale=alt.Scale(type='band', domain=list(range(1, 6))),
),
alt.Y("count()", axis=alt.Axis(title="Number of Ratings"),
scale=alt.Scale(domain=(0, maxCount)),
),
alt.ColorValue("LightGrey"),
).add_selection(highlight_selection) \
.transform_filter(
rating_selection.ref()
)
# We just need to concatenate the plots horizontally, and return the result.
return alt.hconcat(barMean,
barRating,
data=data,
title="{} App Ratings".format(name))