def test_rolling_min(self):
self._check_moment_func(mom.rolling_min, np.min)
a = np.array([1,2,3,4,5])
b = mom.rolling_min(a, window=100, min_periods=1)
assert_almost_equal(b, np.ones(len(a)))
self.assertRaises(ValueError, mom.rolling_min, np.array([1,2,3]), window=3, min_periods=5)
def test_rolling_min(self):
self._check_moment_func(mom.rolling_min, np.min)
a = np.array([1,2,3,4,5])
b = mom.rolling_min(a, window=100, min_periods=1)
assert_almost_equal(b, np.ones(len(a)))
self.assertRaises(ValueError, mom.rolling_min, np.array([1,2,3]), window=3, min_periods=5)
def test_rolling_functions_window_non_shrinkage(self):
# GH 7764
s = Series(range(4))
s_expected = Series(np.nan, index=s.index)
df = DataFrame([[1, 5], [3, 2], [3, 9], [-1, 0]], columns=['A', 'B'])
df_expected = DataFrame(np.nan, index=df.index, columns=df.columns)
df_expected_panel = Panel(items=df.index,
major_axis=df.columns,
minor_axis=df.columns)
functions = [
lambda x: mom.rolling_cov(
x, x, pairwise=False, window=10, min_periods=5),
lambda x: mom.rolling_corr(
x, x, pairwise=False, window=10, min_periods=5),
lambda x: mom.rolling_max(x, window=10, min_periods=5),
lambda x: mom.rolling_min(x, window=10, min_periods=5),
lambda x: mom.rolling_sum(x, window=10, min_periods=5),
lambda x: mom.rolling_mean(x, window=10, min_periods=5),
lambda x: mom.rolling_std(x, window=10, min_periods=5),
lambda x: mom.rolling_var(x, window=10, min_periods=5),
lambda x: mom.rolling_skew(x, window=10, min_periods=5),
lambda x: mom.rolling_kurt(x, window=10, min_periods=5),
lambda x: mom.rolling_quantile(
x, quantile=0.5, window=10, min_periods=5),
lambda x: mom.rolling_median(x, window=10, min_periods=5),
lambda x: mom.rolling_apply(x, func=sum, window=10, min_periods=5),
lambda x: mom.rolling_window(
x, win_type='boxcar', window=10, min_periods=5),
]
for f in functions:
try:
s_result = f(s)
assert_series_equal(s_result, s_expected)
df_result = f(df)
assert_frame_equal(df_result, df_expected)
except (ImportError):
# scipy needed for rolling_window
continue
functions = [
lambda x: mom.rolling_cov(
x, x, pairwise=True, window=10, min_periods=5),
lambda x: mom.rolling_corr(
x, x, pairwise=True, window=10, min_periods=5),
# rolling_corr_pairwise is depracated, so the following line should be deleted
# when rolling_corr_pairwise is removed.
lambda x: mom.rolling_corr_pairwise(x, x, window=10, min_periods=5
),
]
for f in functions:
df_result_panel = f(df)
assert_panel_equal(df_result_panel, df_expected_panel)
def test_rolling_min_how_resample(self):
indices = [datetime(1975, 1, i) for i in range(1, 6)]
# So that we can have 3 datapoints on last day (4, 10, and 20)
indices.append(datetime(1975, 1, 5, 1))
indices.append(datetime(1975, 1, 5, 2))
series = Series(list(range(0, 5)) + [10, 20], index=indices)
# Use floats instead of ints as values
series = series.map(lambda x: float(x))
# Sort chronologically
series = series.sort_index()
# Default how should be min
expected = Series([0.0, 1.0, 2.0, 3.0, 4.0], index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
x = mom.rolling_min(series, window=1, freq="D")
assert_series_equal(expected, x)
def test_rolling_min_how_resample(self):
indices = [datetime(1975, 1, i) for i in range(1, 6)]
# So that we can have 3 datapoints on last day (4, 10, and 20)
indices.append(datetime(1975, 1, 5, 1))
indices.append(datetime(1975, 1, 5, 2))
series = Series(list(range(0, 5)) + [10, 20], index=indices)
# Use floats instead of ints as values
series = series.map(lambda x: float(x))
# Sort chronologically
series = series.sort_index()
# Default how should be min
expected = Series([0.0, 1.0, 2.0, 3.0, 4.0],
index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
x = mom.rolling_min(series, window=1, freq='D')
assert_series_equal(expected, x)
def test_rolling_functions_window_non_shrinkage(self):
# GH 7764
s = Series(range(4))
s_expected = Series(np.nan, index=s.index)
df = DataFrame([[1,5], [3, 2], [3,9], [-1,0]], columns=['A','B'])
df_expected = DataFrame(np.nan, index=df.index, columns=df.columns)
df_expected_panel = Panel(items=df.index, major_axis=df.columns, minor_axis=df.columns)
functions = [lambda x: mom.rolling_cov(x, x, pairwise=False, window=10, min_periods=5),
lambda x: mom.rolling_corr(x, x, pairwise=False, window=10, min_periods=5),
lambda x: mom.rolling_max(x, window=10, min_periods=5),
lambda x: mom.rolling_min(x, window=10, min_periods=5),
lambda x: mom.rolling_sum(x, window=10, min_periods=5),
lambda x: mom.rolling_mean(x, window=10, min_periods=5),
lambda x: mom.rolling_std(x, window=10, min_periods=5),
lambda x: mom.rolling_var(x, window=10, min_periods=5),
lambda x: mom.rolling_skew(x, window=10, min_periods=5),
lambda x: mom.rolling_kurt(x, window=10, min_periods=5),
lambda x: mom.rolling_quantile(x, quantile=0.5, window=10, min_periods=5),
lambda x: mom.rolling_median(x, window=10, min_periods=5),
lambda x: mom.rolling_apply(x, func=sum, window=10, min_periods=5),
lambda x: mom.rolling_window(x, win_type='boxcar', window=10, min_periods=5),
]
for f in functions:
try:
s_result = f(s)
assert_series_equal(s_result, s_expected)
df_result = f(df)
assert_frame_equal(df_result, df_expected)
except (ImportError):
# scipy needed for rolling_window
continue
functions = [lambda x: mom.rolling_cov(x, x, pairwise=True, window=10, min_periods=5),
lambda x: mom.rolling_corr(x, x, pairwise=True, window=10, min_periods=5),
# rolling_corr_pairwise is depracated, so the following line should be deleted
# when rolling_corr_pairwise is removed.
lambda x: mom.rolling_corr_pairwise(x, x, window=10, min_periods=5),
]
for f in functions:
df_result_panel = f(df)
assert_panel_equal(df_result_panel, df_expected_panel)
def aggregated_line_seeds(results, title):
plt.close()
sorted_points = np.array(sorted(results, key=itemgetter(1)))
sorted_time = sorted_points[:, 1] / 60 / 60
sorted_errors = sorted_points[:, 2]
if is_regression:
sorted_errors = np.log10(sorted_errors)
y_mean = stats.rolling_mean(sorted_errors, 5)
# y_std = stats.rolling_std(sorted_errors, 5)
y_upper = stats.rolling_max(sorted_errors, 5)
y_lower = stats.rolling_min(sorted_errors, 5)
plt.plot(sorted_time, y_mean, color="red", label="Rolling mean")
# plt.legend()
plt.fill_between(sorted_time,
y_mean,
y_upper,
facecolor='gray',
interpolate=True,
alpha=0.5)
plt.fill_between(sorted_time,
y_lower,
y_mean,
facecolor='gray',
interpolate=True,
alpha=0.5)
plt.xlabel("Time (h)")
if is_regression:
plt.ylabel("log(RMSE)")
else:
plt.ylabel("% class. error")
plt.ylim(0, 100)
plt.margins(0.05, 0.05)
plt.title(title)
plt.savefig("%s/plots%s/trajectories-%s.aggregated.png" %
(os.environ['AUTOWEKA_PATH'], suffix, title),
bbox_inches='tight')
def llv(s, n):
return moments.rolling_min(s, n)
# ax.set_yscale('log')
# ax.set_xlim(0,30)
# colors = sns.color_palette("husl", 25)
# for i in range(0,25):
# ax.scatter(time_by_seed[i], error_by_seed[i], c=cm.hsv(i/25.,1), s=[30]*len(time_by_seed[i]))
# ax.scatter(time_by_seed[i], error_by_seed[i], c=[colors[i]]*len(time_by_seed[i]), s=[30]*len(time_by_seed[i]))
ax1.set_xlabel('Time (h)')
ax1.set_ylabel('RMSE')
ax1.set_xlim(-1, 30)
y_mean = stats.rolling_mean(sorted_errors, 5)
y_std = stats.rolling_std(sorted_errors, 5)
# y_upper = y_mean + 2*y_std
y_upper = stats.rolling_max(sorted_errors, 5)
# y_lower = y_mean - 2*y_std
y_lower = stats.rolling_min(sorted_errors, 5)
sorted_data = DataFrame(data=sorted_points, columns=['time', 'binned_time', 'error', 'seed'])
# sns.jointplot("binned_time", "error", sorted_data)
# ax1.scatter(sorted_binned_time, sorted_errors)
ax1.plot(sorted_time, y_mean, color="red", label="Rolling mean")
# ax1.errorbar(sorted_binned_time, sorted_errors, marker='o', ms=8, yerr=3*y_std, ls='dotted', label="Rolling mean")
ax1.legend()
ax1.fill_between(sorted_time, y_mean, y_upper, facecolor='gray', interpolate=True, alpha=0.5)
ax1.fill_between(sorted_time, y_lower, y_mean, facecolor='gray', interpolate=True, alpha=0.5)
if not os.path.isdir("plots"):
os.mkdir("plots")
#fig.savefig("plots/points.png", bbox_inches='tight')
fig.savefig("%s/plots%s/points-%s.png" % (os.environ['AUTOWEKA_PATH'], suffix, title), bbox_inches='tight')
# plt.show()
# ax.set_yscale('log')
# ax.set_xlim(0,30)
# colors = sns.color_palette("husl", 25)
# for i in range(0,25):
# ax.scatter(time_by_seed[i], error_by_seed[i], c=cm.hsv(i/25.,1), s=[30]*len(time_by_seed[i]))
# ax.scatter(time_by_seed[i], error_by_seed[i], c=[colors[i]]*len(time_by_seed[i]), s=[30]*len(time_by_seed[i]))
ax1.set_xlabel('Time (h)')
ax1.set_ylabel('RMSE')
ax1.set_xlim(-1, 30)
y_mean = stats.rolling_mean(sorted_errors, 5)
y_std = stats.rolling_std(sorted_errors, 5)
# y_upper = y_mean + 2*y_std
y_upper = stats.rolling_max(sorted_errors, 5)
# y_lower = y_mean - 2*y_std
y_lower = stats.rolling_min(sorted_errors, 5)
sorted_data = DataFrame(data=sorted_points,
columns=['time', 'binned_time', 'error', 'seed'])
# sns.jointplot("binned_time", "error", sorted_data)
# ax1.scatter(sorted_binned_time, sorted_errors)
ax1.plot(sorted_time, y_mean, color="red", label="Rolling mean")
# ax1.errorbar(sorted_binned_time, sorted_errors, marker='o', ms=8, yerr=3*y_std, ls='dotted', label="Rolling mean")
ax1.legend()
ax1.fill_between(sorted_time,
y_mean,
y_upper,
facecolor='gray',
interpolate=True,
alpha=0.5)
ax1.fill_between(sorted_time,
y_lower,
def llv(s, n):
return moments.rolling_min(s, n)
