def test_find_best_interval_input():
# checking functions raise the correct errors for wrong input
# time_df is not DataFrame
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=5, strain_num=2)
assert excinfo.value.args[0] == "df should be pandas DataFrame"
# strain_num is not integer in 0,1,2
row_i = np.hstack(
(np.zeros(13), np.ones(10), np.ones(10) * 2, np.ones(10) * 3))
time_df_eg = np.vstack((row_i, row_i, row_i))
time_df_eg = pd.DataFrame(time_df_eg)
time_df_eg.rename(columns={0: 'strain'}, inplace=True)
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg, strain_num=3)
assert excinfo.value.args[0] == "strain_num can only be 0, 1, 2"
# interval_length_initial is a numpy array with positive integers
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg,
strain_num=0,
interval_length_initial=3)
assert excinfo.value.args[0] == "interval_length_initial positive np.array"
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg,
strain_num=0,
interval_length_initial=np.array([1, 2, -1]))
assert excinfo.value.args[0] == "interval_length_initial positive np.array"
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg,
strain_num=0,
interval_length_initial=np.array([1, 2, 3.1]))
assert excinfo.value.args[0] == "interval_length_initial positive np.array"
def test_find_best_interval_input():
# checking functions raise the correct errors for wrong input
# time_df is not DataFrame
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=5, strain_num=2)
assert excinfo.value.args[0] == "df should be pandas DataFrame"
# strain_num is not integer in 0,1,2
row_i = np.hstack((np.zeros(13), np.ones(10),
np.ones(10)*2, np.ones(10)*3))
time_df_eg = np.vstack((row_i, row_i, row_i))
time_df_eg = pd.DataFrame(time_df_eg)
time_df_eg.rename(columns={0: 'strain'}, inplace=True)
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg, strain_num=3)
assert excinfo.value.args[0] == "strain_num can only be 0, 1, 2"
# interval_length_initial is a numpy array with positive integers
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg, strain_num=0,
interval_length_initial=3)
assert excinfo.value.args[0] == "interval_length_initial positive np.array"
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg, strain_num=0,
interval_length_initial=np.array([1, 2, -1]))
assert excinfo.value.args[0] == "interval_length_initial positive np.array"
with pytest.raises(ValueError) as excinfo:
find_best_interval(df=time_df_eg, strain_num=0,
interval_length_initial=np.array([1, 2, 3.1]))
assert excinfo.value.args[0] == "interval_length_initial positive np.array"
def test_find_best_interval():
row_i = np.hstack((np.zeros(40)))
time_df_eg = np.vstack((row_i, row_i, row_i))
time_df_eg = pd.DataFrame(time_df_eg)
time_df_eg.rename(columns={0: 'strain'}, inplace=True)
time, fake, score = find_best_interval(time_df_eg, 0,
np.arange(10, 40, 10))
assert time == 10
assert np.array_equal(fake, np.zeros(40))
assert 1 - score < 0.05
def test_find_best_interval():
row_i = np.hstack((np.zeros(40)))
time_df_eg = np.vstack((row_i, row_i, row_i))
time_df_eg = pd.DataFrame(time_df_eg)
time_df_eg.rename(columns={0: 'strain'}, inplace=True)
time, fake, score = find_best_interval(time_df_eg, 0,
np.arange(10, 40, 10))
assert time == 10
assert np.array_equal(fake, np.zeros(40))
assert 1-score < 0.05
def plot_dynamics(df, strain_num,
interval_length_initial=np.arange(600, 7800, 600),
plot_time_range=np.arange(36000, 36100, 1)):
r"""
returns a plot that can help understand the
behavior dynamics that are obtained from the best
simulation. The data used as input is the pandas
DataFrame generated by function create_time_matrix.
The output is a plot that summarizes the dynamics
of a fake mouse of the given strain_num. The
strain_num could be chosen. Of note is that
0 represents IS, 1 represents eating, 2 represents
drinking, 3 represents others activity in AS. In the
plot, blue represents IS, bright green represents eating,
yellow represents drinking, and red represents
other activities in AS.
Parameters
----------
df: Pandas.DataFrame
a huge data frame containing info on strain, mouse
no., mouse day, and different states at chosen time
points.
starin_num: int
an integer specifying the desired mouse strain.
strain_num is 0, 1, or 2.
interval_length_initial: numpy.ndarray
a numpy.ndarray specifying the range of time interval
that it optimizes on.
plot_time_range: numpy.ndarray
a numpy.ndarray specifying the range of time range
of the plot.
Returns
-------
dynamics_plot: plot
a plot of behavior dynamics of a fake mouse of the
given strain_num. The x-axis is the time stamps that
start from 0. For strain_num = 0, the x-aixs is from
0 to 92,400. For stain_num = 1, the x-axis is from 0
90,000. For strain_num = 2, the x-axis is from 0 to
88,800. We assign different colors for different
states. In the plot, blue represents IS, bright green
represents eating, yellow represents drinking,
and red represents other activities in AS.
Examples
--------
>>> row_i = np.hstack((np.zeros(40)))
>>> time_df_eg = np.vstack((row_i, row_i, row_i))
>>> time_df_eg = pd.DataFrame(time_df_eg)
>>> time_df_eg.rename(columns={0:'strain'}, inplace=True)
>>> plot_dynamics_plot(time_df_eg, 0,
np.arange(10, 40, 10), np.arange(0, 40, 1))
"""
# check all the inputs
condition_df = (type(df) == pd.core.frame.DataFrame)
condition_strain_num = (strain_num in (0, 1, 2))
condition_interval_length_initial = (type(interval_length_initial) ==
np.ndarray and
np.sum(interval_length_initial > 0) ==
len(interval_length_initial) and
all(isinstance(i, np.int64) for i
in interval_length_initial))
condition_plot_time_range = (type(plot_time_range) ==
np.ndarray and
np.sum(plot_time_range > 0) ==
len(plot_time_range) and
all(isinstance(i, np.int64) for i
in plot_time_range))
if not condition_df:
raise ValueError("df should be pandas DataFrame")
if not condition_strain_num:
raise ValueError("strain_num can only be 0, 1, 2")
if not condition_interval_length_initial:
raise ValueError("interval_length_initial positive np.array")
if not condition_plot_time_range:
raise ValueError("plot_time_range positive np.array")
value_array = find_best_interval(df, strain_num)[1][plot_time_range]
value_list = list(value_array)
time_list = list(plot_time_range)
fig, dynamics_plot = plt.subplots(figsize=(6, 1))
dynamics_plot.scatter(time_list, [1] * len(time_list),
c=value_list, marker='s', s=100)
dynamics_plot.yaxis.set_visible(False)
dynamics_plot.xaxis.set_ticks_position('bottom')
dynamics_plot.get_yaxis().set_ticklabels([])
plt.show()
def plot_dynamics(df,
strain_num,
interval_length_initial=np.arange(600, 7800, 600),
plot_time_range=np.arange(36000, 36100, 1)):
r"""
returns a plot that can help understand the
behavior dynamics that are obtained from the best
simulation. The data used as input is the pandas
DataFrame generated by function create_time_matrix.
The output is a plot that summarizes the dynamics
of a fake mouse of the given strain_num. The
strain_num could be chosen. Of note is that
0 represents IS, 1 represents eating, 2 represents
drinking, 3 represents others activity in AS. In the
plot, blue represents IS, bright green represents eating,
yellow represents drinking, and red represents
other activities in AS.
Parameters
----------
df: Pandas.DataFrame
a huge data frame containing info on strain, mouse
no., mouse day, and different states at chosen time
points.
starin_num: int
an integer specifying the desired mouse strain.
strain_num is 0, 1, or 2.
interval_length_initial: numpy.ndarray
a numpy.ndarray specifying the range of time interval
that it optimizes on.
plot_time_range: numpy.ndarray
a numpy.ndarray specifying the range of time range
of the plot.
Returns
-------
dynamics_plot: plot
a plot of behavior dynamics of a fake mouse of the
given strain_num. The x-axis is the time stamps that
start from 0. For strain_num = 0, the x-aixs is from
0 to 92,400. For stain_num = 1, the x-axis is from 0
90,000. For strain_num = 2, the x-axis is from 0 to
88,800. We assign different colors for different
states. In the plot, blue represents IS, bright green
represents eating, yellow represents drinking,
and red represents other activities in AS.
Examples
--------
>>> row_i = np.hstack((np.zeros(40)))
>>> time_df_eg = np.vstack((row_i, row_i, row_i))
>>> time_df_eg = pd.DataFrame(time_df_eg)
>>> time_df_eg.rename(columns={0:'strain'}, inplace=True)
>>> plot_dynamics_plot(time_df_eg, 0,
np.arange(10, 40, 10), np.arange(0, 40, 1))
"""
# check all the inputs
condition_df = (type(df) == pd.core.frame.DataFrame)
condition_strain_num = (strain_num in (0, 1, 2))
condition_interval_length_initial = (
type(interval_length_initial) == np.ndarray
and np.sum(interval_length_initial > 0) == len(interval_length_initial)
and all(isinstance(i, np.int64) for i in interval_length_initial))
condition_plot_time_range = (
type(plot_time_range) == np.ndarray
and np.sum(plot_time_range > 0) == len(plot_time_range)
and all(isinstance(i, np.int64) for i in plot_time_range))
if not condition_df:
raise ValueError("df should be pandas DataFrame")
if not condition_strain_num:
raise ValueError("strain_num can only be 0, 1, 2")
if not condition_interval_length_initial:
raise ValueError("interval_length_initial positive np.array")
if not condition_plot_time_range:
raise ValueError("plot_time_range positive np.array")
value_array = find_best_interval(df, strain_num)[1][plot_time_range]
value_list = list(value_array)
time_list = list(plot_time_range)
fig, dynamics_plot = plt.subplots(figsize=(6, 1))
dynamics_plot.scatter(time_list, [1] * len(time_list),
c=value_list,
marker='s',
s=100)
dynamics_plot.yaxis.set_visible(False)
dynamics_plot.xaxis.set_ticks_position('bottom')
dynamics_plot.get_yaxis().set_ticklabels([])
plt.show()