def movie(compare_column=None, df=None):
'''
Creates an animation of the beaches E. coli levels represented as circles.
The circle's radius is proportional to the log of the E. coli levels.
Additionally, when the E. coli level is above the threshold of 235 PPM,
the circle color changes from blue to purple. You can optionally choose
to vary the background color of the animation with another column of data,
however, this does not seem like a great way to visualize the relationship
between E. coli levels and another data-stream.
Inputs
------
compare_column : The name or index of the column that will be used to vary
the background color. If compare_column is None, then the
background color will remain static.
df : The dataframe to use. If None, then the dataframe will be
read in using read_data.
Returns
-------
anim : The animation object.
Example
-------
>>> import read_data as rd
>>> import visualizations as viz
>>> df = rd.read_data()
>>> viz.movie(df=df)
'''
if df is None:
df = read_data.read_data()
if compare_column is None:
to_compare = False
else:
to_compare = True
if to_compare:
compare_min = df[compare_column].dropna().min()
compare_max = df[compare_column].dropna().max()
bg_min_color = np.array([.75, .5, .2])
bg_max_color = np.array([.999, .999, 0.9])
file_name = '../data/ExternalData/Beach_Locations.csv'
beach_locs = read_data.read_locations(file_name)
# compute Mercator projection of lat/longs
phi = 0.730191653
beach_locs['Latitude'] = beach_locs['Latitude'] * 110574.0
beach_locs['Longitude'] = beach_locs['Longitude'] * 111320.0 * np.cos(phi)
lat_min = beach_locs['Latitude'].min()
lat_max = beach_locs['Latitude'].max()
lat_rng = lat_max - lat_min
lon_min = beach_locs['Longitude'].min()
lon_max = beach_locs['Longitude'].max()
lon_rng = lon_max - lon_min
def generate_index():
for timestamp in df.index.unique():
readings = df.ix[timestamp, 'Escherichia.coli']
if to_compare:
compare = df.ix[timestamp, compare_column]
if type(compare) is pd.Series:
compare = compare.dropna().mean()
if np.isnan(compare):
continue
if ((type(readings) is np.float64 and not np.isnan(readings)) or
(type(readings) is not np.float64 and readings.count())):
if not to_compare:
compare = None
yield timestamp, compare
def animate(timestamp_and_compare):
timestamp = timestamp_and_compare[0]
compare = timestamp_and_compare[1]
if to_compare:
compare = (compare - compare_min) / compare_max
bg_color = bg_min_color * compare + bg_max_color * (1. - compare)
ax.set_axis_bgcolor(bg_color)
for i, b in enumerate(beach_locs['Beach']):
beach_filt = df.ix[timestamp, 'Client.ID'] == b
beach_skipped = False
try:
if not beach_filt.sum() == 1:
beach_skipped = True
except AttributeError: # is a boolean
if not beach_filt:
beach_skipped = True
if beach_skipped:
ecoli = 0
else:
ecoli = float(df.ix[timestamp, 'Escherichia.coli'][beach_filt])
r = 200 * np.log(ecoli)
if b in circle_indexes:
ax.artists[circle_indexes[b]].set_radius(r)
if ecoli >= 235:
ax.artists[circle_indexes[b]].set_facecolor(
(0.301, 0, 1, 0.75))
else:
ax.artists[circle_indexes[b]].set_facecolor(
(0, 0.682, 1, 0.75))
else:
circ = plt.Circle(
(beach_locs.ix[i, 'Longitude'], beach_locs.ix[i,
'Latitude']),
radius=r,
edgecolor='none')
ax.add_artist(circ)
circle_indexes[b] = len(ax.artists) - 1
if ecoli >= 235:
ax.artists[circle_indexes[b]].set_facecolor(
(0.301, 0, 1, 0.75))
else:
ax.artists[circle_indexes[b]].set_facecolor(
(0, 0.682, 1, 0.75))
ax.title.set_text(timestamp.strftime('%d %B %Y'))
return ax
fig = plt.figure(figsize=(18, 10))
ax = plt.gcf().gca()
ax.set_xlim([lon_min - lon_rng * 0.4, lon_max + lon_rng * 0.15])
ax.set_ylim([lat_min - lat_rng * 0.2, lat_max + lat_rng * 0.2])
ax.set_aspect('equal')
circle_indexes = {}
anim = animation.FuncAnimation(fig, animate, generate_index, repeat=False)
plt.show(block=TO_BLOCK)
return anim
def movie(compare_column=None, df=None):
'''
Creates an animation of the beaches E. coli levels represented as circles.
The circle's radius is proportional to the log of the E. coli levels.
Additionally, when the E. coli level is above the threshold of 235 PPM,
the circle color changes from blue to purple. You can optionally choose
to vary the background color of the animation with another column of data,
however, this does not seem like a great way to visualize the relationship
between E. coli levels and another data-stream.
Inputs
------
compare_column : The name or index of the column that will be used to vary
the background color. If compare_column is None, then the
background color will remain static.
df : The dataframe to use. If None, then the dataframe will be
read in using read_data.
Returns
-------
anim : The animation object.
Example
-------
>>> import read_data as rd
>>> import visualizations as viz
>>> df = rd.read_data()
>>> viz.movie(df=df)
'''
if df is None:
df = read_data.read_data()
if compare_column is None:
to_compare = False
else:
to_compare = True
if to_compare:
compare_min = df[compare_column].dropna().min()
compare_max = df[compare_column].dropna().max()
bg_min_color = np.array([.75, .5, .2])
bg_max_color = np.array([.999, .999, 0.9])
file_name = '../data/ExternalData/Beach_Locations.csv'
beach_locs = read_data.read_locations(file_name)
# compute Mercator projection of lat/longs
phi = 0.730191653
beach_locs['Latitude'] = beach_locs['Latitude'] * 110574.0
beach_locs['Longitude'] = beach_locs['Longitude'] * 111320.0 * np.cos(phi)
lat_min = beach_locs['Latitude'].min()
lat_max = beach_locs['Latitude'].max()
lat_rng = lat_max - lat_min
lon_min = beach_locs['Longitude'].min()
lon_max = beach_locs['Longitude'].max()
lon_rng = lon_max - lon_min
def generate_index():
for timestamp in df.index.unique():
readings = df.ix[timestamp, 'Escherichia.coli']
if to_compare:
compare = df.ix[timestamp, compare_column]
if type(compare) is pd.Series:
compare = compare.dropna().mean()
if np.isnan(compare):
continue
if ((type(readings) is np.float64 and not np.isnan(readings)) or
(type(readings) is not np.float64 and readings.count())):
if not to_compare:
compare = None
yield timestamp, compare
def animate(timestamp_and_compare):
timestamp = timestamp_and_compare[0]
compare = timestamp_and_compare[1]
if to_compare:
compare = (compare - compare_min) / compare_max
bg_color = bg_min_color * compare + bg_max_color * (1. - compare)
ax.set_axis_bgcolor(bg_color)
for i, b in enumerate(beach_locs['Beach']):
beach_filt = df.ix[timestamp, 'Client.ID'] == b
beach_skipped = False
try:
if not beach_filt.sum() == 1:
beach_skipped = True
except AttributeError: # is a boolean
if not beach_filt:
beach_skipped = True
if beach_skipped:
ecoli = 0
else:
ecoli = float(df.ix[timestamp, 'Escherichia.coli'][beach_filt])
r = 200 * np.log(ecoli)
if b in circle_indexes:
ax.artists[circle_indexes[b]].set_radius(r)
if ecoli >= 235:
ax.artists[circle_indexes[b]].set_facecolor(
(0.301, 0, 1, 0.75))
else:
ax.artists[circle_indexes[b]].set_facecolor(
(0, 0.682, 1, 0.75))
else:
circ = plt.Circle((beach_locs.ix[i,'Longitude'],
beach_locs.ix[i,'Latitude']),
radius=r, edgecolor='none')
ax.add_artist(circ)
circle_indexes[b] = len(ax.artists) - 1
if ecoli >= 235:
ax.artists[circle_indexes[b]].set_facecolor(
(0.301, 0, 1, 0.75))
else:
ax.artists[circle_indexes[b]].set_facecolor(
(0, 0.682, 1, 0.75))
ax.title.set_text(timestamp.strftime('%d %B %Y'))
return ax
fig = plt.figure(figsize=(18,10))
ax = plt.gcf().gca()
ax.set_xlim([lon_min - lon_rng * 0.4, lon_max + lon_rng * 0.15])
ax.set_ylim([lat_min - lat_rng * 0.2, lat_max + lat_rng * 0.2])
ax.set_aspect('equal')
circle_indexes = {}
anim = animation.FuncAnimation(fig, animate, generate_index, repeat=False)
plt.show(block=TO_BLOCK)
return anim
def movie(data_column, lat_longs, df=None):
if df is None:
df = read_data.read_data()
file_name = '../data/ExternalData/Beach_Locations.csv'
beach_locs = read_data.read_locations(file_name)
phi = 0.730191653
beach_locs['Latitude'] = beach_locs['Latitude'] * 110574.0
beach_locs['Longitude'] = beach_locs['Longitude'] * 111320.0 * np.cos(phi)
# lat_longs = np.array(lat_longs)
# lat_longs[:,0] = lat_longs[:,0] * 110574.0
# lat_longs[:,1] = lat_longs[:,1] * 111320.0 * np.cos(phi)
# fig = plt.gcf()
# ax = fig.gca()
lat_min = beach_locs['Latitude'].min()
lat_max = beach_locs['Latitude'].max()
lat_rng = lat_max - lat_min
lon_min = beach_locs['Longitude'].min()
lon_max = beach_locs['Longitude'].max()
lon_rng = lon_max - lon_min
# ax.set_xlim([lon_min - lon_rng * 0.1, lon_max + lon_rng * 0.1])
# ax.set_ylim([lat_min - lat_rng * 0.1, lat_max + lat_rng * 0.1])
# ax.set_aspect('equal')
def generate_index():
for timestamp in df.index.unique():
readings = df.ix[timestamp, 'Escherichia.coli']
if ((type(readings) is np.float64 and not np.isnan(readings)) or
(type(readings) is not np.float64 and readings.count())):
yield timestamp
def animate(timestamp):
for i, b in enumerate(beach_locs['Beach']):
beach_filt = df.ix[timestamp, 'Client.ID'] == b
beach_skipped = False
try:
if not beach_filt.sum() == 1:
beach_skipped = True
except AttributeError: # is a boolean
if not beach_filt:
beach_skipped = True
if beach_skipped:
ecoli = 0
else:
ecoli = float(df.ix[timestamp, 'Escherichia.coli'][beach_filt])
r = 200 * np.log(ecoli)
if b in circle_indexes:
ax.artists[circle_indexes[b]].set_radius(r)
if ecoli >= 235:
ax.artists[circle_indexes[b]].set_facecolor((0.862, 0.357, 0.276, 0.8))
else:
ax.artists[circle_indexes[b]].set_facecolor((0.262, 0.357, 0.576, 0.8))
else:
circ = plt.Circle((beach_locs.ix[i,'Longitude'],
beach_locs.ix[i,'Latitude']),
radius=r)
ax.add_artist(circ)
circle_indexes[b] = len(ax.artists) - 1
if ecoli >= 235:
ax.artists[circle_indexes[b]].set_facecolor((0.862, 0.357, 0.276, 0.8))
else:
ax.artists[circle_indexes[b]].set_facecolor((0.262, 0.357, 0.576, 0.8))
ax.title.set_text(timestamp.strftime('%d %B %Y'))
return ax
fig = plt.figure(figsize=(18,10))
ax = plt.gcf().gca()
ax.set_xlim([lon_min - lon_rng * 0.4, lon_max + lon_rng * 0.15])
ax.set_ylim([lat_min - lat_rng * 0.2, lat_max + lat_rng * 0.2])
ax.set_aspect('equal')
circle_indexes = {}
anim = animation.FuncAnimation(fig, animate, generate_index, repeat=False)
mywriter = animation.FFMpegWriter(fps=30)
anim.save('test.mp4', writer=mywriter)
return anim
