def plot_point_map(gpd_gdf, percentile=0, save_file=None):
"""plot point data on a map"""
# Choose points in which NSE value are bigger than the 25% quartile value range
percentile_data = np.percentile(gpd_gdf['NSE'].values,
percentile).astype(float)
# the result of query is a tuple with one element, but it's right for plotting
data_chosen = gpd_gdf.query("NSE > " + str(percentile_data))
contiguous_usa = gpd.read_file(gplt.datasets.get_path('contiguous_usa'))
proj = gcrs.AlbersEqualArea(central_longitude=-98, central_latitude=39.5)
polyplot_kwargs = {'facecolor': (0.9, 0.9, 0.9), 'linewidth': 0}
pointplot_kwargs = {'hue': 'NSE', 'legend': True, 'linewidth': 0.01}
# ax = gplt.polyplot(contiguous_usa.geometry, projection=proj, **polyplot_kwargs)
ax = gplt.webmap(contiguous_usa, projection=gcrs.WebMercator())
gplt.pointplot(data_chosen, ax=ax, **pointplot_kwargs)
ax.set_title("NSE " + "Map")
plt.show()
if save_file is not None:
plt.savefig(save_file)
# read shape files
q1 = gp.read_file('./Ookla shape data/2020q1')
q2 = gp.read_file('./Ookla shape data/2020q2')
q3 = gp.read_file('./Ookla shape data/2020q3')
q4 = gp.read_file('./Ookla shape data/2020q4')
ma = gp.read_file('./data/export-gisdata.mapc.ma_municipalities').to_crs(
epsg=4326)
# In[57]:
data_2020 = pd.concat([q1, q2, q3, q4])
# In[59]:
ax = gplt.webmap(data_2020, projection=gcrs.WebMercator())
gplt.choropleth(data_2020,
hue='avg_d_kbps',
projection=gcrs.AlbersEqualArea(),
cmap='Greens',
legend=True,
ax=ax)
plt.show()
# In[43]:
# use the location of the centroid of each polygon
data_2020['geometry'] = data_2020['geometry'].centroid
# In[56]:
"""
KDEPlot of Boston AirBnB Locations
==================================
This example demonstrates a combined application of ``kdeplot`` and ``pointplot`` to a
dataset of AirBnB locations in Boston. The result is outputted to a webmap using the nifty
``mplleaflet`` library. We sample just 1000 points, which captures the overall trend without
overwhelming the renderer.
`Click here to see this plot as an interactive webmap.
<https://bl.ocks.org/ResidentMario/868ac097d671df1ed5ec83eed048560c>`_
"""
import geopandas as gpd
import geoplot as gplt
import geoplot.crs as gcrs
import matplotlib.pyplot as plt
boston_airbnb_listings = gpd.read_file(
gplt.datasets.get_path('boston_airbnb_listings'))
ax = gplt.kdeplot(boston_airbnb_listings,
cmap='viridis',
projection=gcrs.WebMercator(),
figsize=(12, 12),
shade=True)
gplt.pointplot(boston_airbnb_listings, s=1, color='black', ax=ax)
gplt.webmap(boston_airbnb_listings, ax=ax)
plt.title('Boston AirBnB Locations, 2016', fontsize=18)
# %% [markdown] Collapsed="false"
# ## Making Maps
# %% Collapsed="false"
f, ax = plt.subplots(dpi = 200)
countries.plot(edgecolor = 'k', facecolor = 'None', linewidth = 0.6, ax = ax)
cities.plot(markersize = 0.5, facecolor = 'red', ax = ax)
lat_am_capitals.plot(markersize = 0.5, facecolor = 'y', ax = ax)
ax.set_title('World Map')
ax.set_axis_off()
# %% [markdown] Collapsed="false"
# ## Static Webmaps
# %% Collapsed="false"
ax = gplt.webmap(countries, projection=gplt.crs.WebMercator(), figsize = (16, 12))
gplt.pointplot(cities, ax=ax, hue = 'POP2015')
# %% [markdown] Collapsed="false"
# ## Aside on Projections
# %% [markdown] Collapsed="false"
# Map projections flatten a globe's surface onto a 2D plane. This necessarily distorts the surface (one of Gauss' lesser known results), so one must choose specific form of 'acceptable' distortion.
#
# By convention, the standard projection in GIS is World Geodesic System(lat/lon - `WGS84`). This is a cylindrical projection, which stretches distances east-west and *results in incorrect distance and areal calculations*. For accurate distance and area calculations, try to use UTM (which divides map into zones). See [epsg.io](epsg.io)
# %% Collapsed="false"
countries.crs
# %% Collapsed="false"
countries_2 = countries.copy()
def plotme(week=weeks[-1][0],
startweek=weeks[-1][0],
webmap=False,
setnorm=False,
stddev=1,
savename='RecentMap.jpg',
closefig=False,
figsize=(25, 14)):
projectioncode = 'EPSG:3395'
fig = plt.figure(figsize=figsize)
spec = gridspec.GridSpec(ncols=2, nrows=1, width_ratios=[1, 10])
colname = week.strftime('%Y-%m-%d') + '_chg'
validmask = np.logical_not(
np.logical_or(np.isnan(df[colname]), np.isinf(df[colname])))
normmin, normmax = (df[validmask][colname].min(),
df[validmask][colname].max())
print("DataMin=%d\tDataMax=%d" % (normmin, normmax))
if webmap:
ax1 = fig.add_subplot(spec[1], projection=gcrs.WebMercator())
gplt.webmap(df, ax=ax1)
projectioncode = 'EPSG:3785'
else:
ax1 = fig.add_subplot(spec[1], projection=gcrs.Mercator())
if setnorm:
norm = Normalize(vmin=setnorm[0], vmax=setnorm[1], clip=True)
else:
#maxmin = np.max(np.abs([df[colname].min(),df[colname].max()]))
#norm = Normalize(vmin=-maxmin,vmax=maxmin)
norm = Normalize(vmin=normmin, vmax=normmax.max())
gplt.choropleth(df[validmask],
zorder=10,
hue=colname,
norm=norm,
legend=True,
ax=ax1,
extent=extent,
edgecolor='black',
cmap='RdYlGn_r')
#color NaNs and inf
gplt.polyplot(df[np.logical_not(validmask)],
facecolor='#0000FF',
zorder=20,
ax=ax1,
extent=extent)
fig.suptitle(
"Covid-19 Week to Week %% Change in New Cases by Parish for %s" %
week.strftime('%b %d, %Y').ljust(14))
ax2 = fig.add_subplot(spec[0])
ax2.set_title('Weekly New Cases for Louisiana')
ax2.barh(la_series.index,
la_series,
color='y',
height=6.5,
label='Weekly New Cases')
ax2.axhline(week, color='red', label='Current Week')
ax2.yaxis.set_major_formatter(DateFormatter('%b %d'))
for tick in ax2.get_yticklabels():
tick.set_rotation(90)
ax2.legend()
fig.text(0.78,
0.93,
week.strftime('%b %d, %Y').rjust(12),
fontsize=18,
fontfamily='monospace',
bbox=dict(boxstyle='round', facecolor='#ffffa8', alpha=0.7))
#get outliers
mean = df[validmask][colname].mean()
outdev = df[validmask][colname].std() * stddev
print("outdev=%d" % outdev)
label_outliers = df[np.abs(df[colname] - mean) > outdev]
labels = label_outliers.append(label_places).drop_duplicates()
centroids = labels['geometry'].to_crs(projectioncode).centroid
for x, y, name in zip(centroids.x, centroids.y, labels['NAME']):
ax1.annotate(name.replace(' ', "\n"),
xy=(x, y),
xytext=(0, -6),
textcoords="offset points",
zorder=50,
ha='center',
va='top')
centroids = df['geometry'].to_crs(projectioncode).centroid
for x, y, value in zip(centroids.x, centroids.y, df[colname]):
ax1.annotate(labelgen(value),
xy=(x, y),
xytext=(0, 6),
textcoords="offset points",
zorder=50,
ha='center',
va='center',
fontsize=15,
bbox=dict(boxstyle='round',
facecolor=getfacecolor(value),
alpha=0.4))
fig.tight_layout()
if savename != None:
fig.savefig(savename)
if closefig:
plt.close()
return norm
gdf = geopandas.GeoDataFrame(new_data_reduced, geometry='Coordinates')
if DEBUG==1: print(" Sample of the geospatial dataframe: \n", gdf.head())
# Convert from pandas data frame to a geopandas dataframe
if DEBUG==1: print(" Boroughs sample :\n\n", boroughs.head() , "\n\n Collisions sample:\n\n" , collisions.head())
new_data_reduced.rename(columns={'Coordinates':'geometry'}, inplace='True')
final_df = geopandas.GeoDataFrame(new_data_reduced)
if DEBUG==0: print ('\n\nType of new data reduced: ',type(final_df)\
,'\n\n Newly renamed columns of new_data_reduced :\n\n', final_df.head())
# Now making the geoplot of the plots with the
#making the heatmap
boroughs = geopandas.read_file(geoplot.datasets.get_path('nyc_boroughs'))
ax = geoplot.kdeplot(
final_df,# clip=boroughs.geometry,
shade=True, cmap='Reds',
projection=geoplot.crs.WebMercator())
geoplot.polyplot(boroughs, ax=ax, zorder=1)
geoplot.webmap(boroughs,ax=ax,zoom=12)
plt.show()
# Trying to plot as point data over webmap instead of a heat map over a webmap
ax = geoplot.webmap(boroughs, projection=geoplot.crs.WebMercator(), zoom=12)
geoplot.pointplot(final_df[final_df['Asset_Area'] > 10.0 ] , ax=ax)
geoplot.polyplot(boroughs, ax=ax, zorder=1)
plt.show()
stopwords=STOPWORDS).generate(' '.join(
incidents_gdf['cat_calc'].values))
fig = plt.figure(figsize=(10, 8), facecolor='k', edgecolor='k')
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.tight_layout(pad=1)
plt.show()
############################################
# Which incidents are most common, in pie-chart form?
df['cat_calc'].value_counts().plot.pie(legend=False, figsize=(15, 6))
############################################
# Where are each incident in Arlington County, plotted as points on a web map?
# as simple points
ax = gplt.webmap(both_df, projection=gcrs.WebMercator())
gplt.pointplot(both_df, ax=ax, marker=".",
alpha=0.80) # marker could be o or .
_ = ax.axis('off')
ax.set_title("Police incidents in Arlington County, VA")
plt.show()
# give a 1-to-n (0 to 1) number for each category and assign to 'arbitrary_hue' value based on 'cat_calc' value
categories_split_str = [' '.join(c) for c in categories_split] + ['OTHER']
both_df['arbitrary_hue'] = both_df['cat_calc'].apply(lambda c: float(
categories_split_str.index(c)) / (len(categories_split_str) - 1))
ax = gplt.webmap(both_df, projection=gcrs.WebMercator())
gplt.pointplot(both_df, ax=ax, marker=".", hue='arbitrary_hue',
alpha=0.80) # marker could be o or .
_ = ax.axis('off')
ax.set_title("Police incidents in Arlington County, VA")
def plotting_heat_map(file_name='toronto_data.csv',\
json_name='https://raw.githubusercontent.com/jasonicarter/toronto-geojson/master/toronto_crs84.geojson',\
max_distance=15,\
min_bedrooms=1,\
max_bedrooms=1,\
max_rent=5000):
""" Plots a heat map based on the DataFrame supplied to the function.
The function plots rents by number of bedrooms on a map
Args:
file_name: file name to be called (default='toronto_data.csv')
json_name: file address for the map of the city on which data is superimposed
(defualt='https://raw.githubusercontent.com/jasonicarter/toronto-geojson/master/toronto_crs84.geojson')
max_distance: exclude renatal that are more than max_distance
away from the center (default=5)
min_bedrooms: excludes rentals with less than min_bedrooms bedrooms
(default=0)
max_bedrooms: excludes rentals with more than max_bedrooms bedrooms
(default=0)
max_rent: excludes rentals that cost more than max_rent
(default=5000)
"""
# imports the .csv file and tells the data from that coordaintes are a list
df = pd.read_csv(file_name, converters={'coordinates': literal_eval})
# breaks down the coordinates to lat and long
df[['lat', 'long']] = pd.DataFrame(df.coordinates.values.tolist(),
index=df.index)
# drops all the lat and long na observations
df = df.dropna(subset=['lat'])
df = df[df['distance'] <= max_distance]
df = df[df['rent'] <= max_rent]
# drops all rentals with more than max_bedrooms and less than min_bedrooms
df = df[df['bedroom'] >= min_bedrooms]
df = df[df['bedroom'] <= max_bedrooms]
# creates a new column that keeps both lat and long
gdf = geopd.GeoDataFrame(df,
geometry=geopd.points_from_xy(df.long, df.lat))
# create backgroup map with city geojson data
city_json = 'https://raw.githubusercontent.com/jasonicarter/toronto-geojson/master/toronto_crs84.geojson'
# loading the map for the city
city_map = geopd.read_file(city_json)
# creating the map
ax = gplt.webmap(city_map, projection=gcrs.WebMercator())
# plots rents by color on the map of the city
gplt.pointplot(gdf,
ax=ax,
hue='rent',
legend=True,
projection=gcrs.AlbersEqualArea())
# saves the plot as a .png file
plt.savefig('heat_map_' + file_name.replace('.csv', '.png'))