def get_rmcorr_for_sensitivities_by_participant(
sensitivities_by_participant: List[List[InterstimSensitivities]], ):
df = _get_dataframe_for_sensitivities_by_participant(
sensitivities_by_participant)
model = ols("dprime ~ C(subject) + distance", data=df).fit()
rm_corr = pg.rm_corr(df, x="distance", y="dprime", subject="subject")
return (
model.params["distance"],
rm_corr.at["rm_corr", "r"],
rm_corr.at["rm_corr", "CI95%"],
rm_corr.at["rm_corr", "pval"],
)
shapiro_samples.append([x for x in data_points.T])
shapiro_names.append(['{} {} {} {}'.format(metric_type, fb_type, k, th) for k in range(1, 16)])
fb_data_points.append(data_points[:, :])
ax = (axes[fb_typs_axes[fb_type]]
if metric_type=='magnitude' else axes2[metric_types_ax[metric_type], fb_typs_axes[fb_type]])
if th == threshold or metric_type=='magnitude':
ax.errorbar(np.arange(len(unique_blocks))+1, data_points.mean(0),
2*data_points.std(0) / np.sqrt(data_points.shape[0]), color=fb_typs_colors[fb_type],
linewidth=0.75, elinewidth=0.75, linestyle='', marker='o', markersize=2, label=fb_type, zorder=100)
ax.plot(np.arange(len(unique_blocks))+1, data_points.T, color=fb_typs_colors[fb_type],
linewidth=0.5, linestyle='-', markersize=2, label=fb_type, alpha=0.25)
df = metrics_df.query('metric_type=="{}" & fb_type=="{}"'.format(metric_type, fb_type))
df['k'] = df['k'].astype(int)
s = r'$\rho_{CI95}$=' + rm_corr(df, 'k', 'metric', 'subj_id')['CI95%'].values[0]
lim = metric_types_lims[metric_type]
ax.text(1, lim[0] + (lim[1]-lim[0])*0.9, s, size=7)
if fb_typs_axes[fb_type] == 0: ax.set_ylabel(metric_type)
ax.set_ylim(*lim)
ax.set_yticks([lim[0], 1., lim[1]])
stats = []
stats_extra = []
z_scores = []
ds = []
ps = []
def time_series_with_biometric_bar_plot(biometric_source_data_1,
biometric_source_data_2,
sample_source_data_1,
sample_source_data_2, view_1, view_2,
selection_dict):
# parse selections
biometric = selection_dict['biometric']
metabolite = selection_dict['metabolite']
user = selection_dict['user']
scale = selection_dict['scale']
start_time = pd.to_datetime('8/22/2018')
end_time = pd.to_datetime('9/1/2018')
# set up data and relevant stats
if user == "Both":
# run rm_corr
title = 'Daily total/average: {}'.format(biometric)
# .tolist() causing refresh error
x = list(biometric_source_data_1.data[biometric]) + list(
biometric_source_data_2.data[biometric])
y = list(np.log2(biometric_source_data_1.data[metabolite])) \
+ list(np.log2(biometric_source_data_2.data[metabolite]))
subject = ["Subject1"] * len(biometric_source_data_1.data[metabolite]) \
+ ["Subject2"] * len(biometric_source_data_2.data[metabolite])
df = pd.DataFrame({
'x': x,
'y': y,
'subject': subject,
})
r, p, dof = pg.rm_corr(data=df, x='x', y='y', subject='subject')
title = "Daily total/average: {} vs. log2 (Avg. Int.) {}; RM Corr : r = {}, p = {}".format(
biometric, metabolite, round(r, 3), round(p, 3))
# get biometric max
biometric_max = max(x)
# get metabolite intensity min
metabolite_intensities = list(sample_source_data_1.data[metabolite]) \
+ list(sample_source_data_2.data[metabolite])
intensity_min, intensity_max = min(metabolite_intensities), \
max(metabolite_intensities)
elif user == "Subject1":
# calculate Spearman's Rho for Subject1
x = biometric_source_data_1.data[biometric]
y = np.log2(biometric_source_data_1.data[metabolite])
corr_df = pg.corr(x, y, method='skipped')
coef = corr_df.iloc[0]['r']
p = corr_df.iloc[0]['p-val']
#print(corr_df)
title = "Daily average {} vs. log2(Avg. Int.) {}; Spearman's Rho: {}, p = {}".format(
biometric, metabolite, round(coef, 3), round(p, 5))
# get biometric max
biometric_max = max(x)
# get metabolite intensity min
metabolite_intensities = list(sample_source_data_1.data[metabolite])
intensity_min, intensity_max = min(metabolite_intensities), \
max(metabolite_intensities)
elif user == "Subject2":
# calculate Spearman's Rho
x = biometric_source_data_2.data[biometric]
y = np.log2(biometric_source_data_2.data[metabolite])
corr_df = pg.corr(x, y, method='skipped')
coef = corr_df.iloc[0]['r']
p = corr_df.iloc[0]['p-val']
#print(corr_df)
title = "Daily average {} vs. log2(Avg. Int.) {}; Spearman's Rho: {}, p = {}".format(
biometric, metabolite, round(coef, 3), round(p, 5))
# get biometric max
biometric_max = max(x)
# get metabolite intensity range
metabolite_intensities = sample_source_data_2.data[metabolite]
intensity_min, intensity_max = min(metabolite_intensities), \
max(metabolite_intensities)
# Set up figure and formatting
p = figure(
title=title,
tools=tools,
x_axis_type="datetime",
plot_width=800,
plot_height=400,
x_range=[start_time, end_time],
y_range=[intensity_min, intensity_max],
)
#tooltips = [("sample", "@SampleID")])
# Setting the second y axis range name and range
biometric_max_start = biometric_max * 0.10
biometric_range_end = biometric_max * 1.10
p.extra_y_ranges = {
"biometric_axis":
Range1d(start=biometric_max_start, end=biometric_range_end)
}
# Adding the second axis to the plot.
p.add_layout(LinearAxis(y_range_name="biometric_axis"), 'right')
p.xaxis.ticker = DaysTicker(days=np.arange(1, 59))
p.xaxis.formatter = DatetimeTickFormatter(
hours=["%d %B %Y"],
days=["%d %B %Y"],
months=["%d %B %Y"],
years=["%d %B %Y"],
)
p.output_backend = "svg"
p.xaxis.axis_label = None
p.toolbar.logo = None
p.xaxis.major_label_orientation = pi / 4
p.xgrid.grid_line_color = None
p.ygrid.grid_line_color = None
p.outline_line_color = None
p.yaxis.axis_label = metabolite + " {}".format(scale)
p.yaxis[1].axis_label = biometric
### Now for actual data ###
# Have to make width huge, since Datetime has millisecond resolution:
# https://stackoverflow.com/questions/45711567/categorical-y-axis-and-datetime-x-axis-with-bokeh-vbar-plot
# 1 hr * 4
millisecond_width = 3600000 * 24
if user == "Both" or user == "Subject1":
# time series data
legend_title = "Subject 1 [{}]".format(metabolite)
p.line('Datetime',
metabolite,
source=sample_source_data_1,
color='red')
p.circle('Datetime',
metabolite,
source=sample_source_data_1,
color="red",
size=5,
alpha=0.5,
view=view_1,
hover_color="black")
# biometric data
legend_title = "Subject 1 Daily Total {}".format(biometric)
p.step('Datetime',
y=biometric,
color="red",
mode="center",
line_dash="dashed",
source=biometric_source_data_1,
legend=legend_title,
y_range_name="biometric_axis")
p.vbar('Datetime',
top=biometric,
fill_color="red",
width=millisecond_width,
line_color=None,
alpha=0.3,
source=biometric_source_data_1,
y_range_name="biometric_axis")
# overwrite
if user == "Both" or user == "Subject2":
# time series data
legend_title = "Subject 2 [{}]".format(metabolite)
p.line('Datetime',
metabolite,
source=sample_source_data_2,
color='blue')
p.circle('Datetime',
metabolite,
source=sample_source_data_2,
color="blue",
size=5,
alpha=0.5,
view=view_2,
hover_color="black")
# biometric data
legend_title = "Subject 2 Daily Total {}".format(biometric)
p.step('Datetime',
y=biometric,
color="blue",
mode="center",
line_dash="dashed",
source=biometric_source_data_2,
legend=legend_title,
y_range_name="biometric_axis")
p.vbar(x='Datetime',
top=biometric,
fill_color="blue",
width=millisecond_width,
line_color=None,
alpha=0.3,
source=biometric_source_data_2,
y_range_name="biometric_axis")
# Light cycle formatting, this needs to come second for tool tips to render
vline_list = []
for datetime in pd.date_range(start='8/22/2018', end='9/1/2018'):
vline = Span(
location=datetime,
dimension='height',
line_color='grey',
#this should creat a ~6 hr window around midnight, to simulate
# the dark cycle during this time period
line_width=24,
line_dash='solid',
line_alpha=0.3)
vline_list.append(vline)
p.renderers.extend(vline_list)
return p
def print_rm_corr(df_lab, df_wild):
"""
print the rm_corr.
"""
print("\n\nGETTING RM_CORR:")
print('\nIN-LAB:')
print('ActiGraph VM3 vs Ainsworth:')
g = pg.plot_rm_corr(data=df_lab,
x='MET (VM3)',
y='MET (Ainsworth)',
subject='Participant')
output = pg.rm_corr(data=df_lab,
x='MET (VM3)',
y='MET (Ainsworth)',
subject='Participant')
print(output)
print('\nWRIST vs Ainsworth:')
g = pg.plot_rm_corr(data=df_lab,
x='estimation',
y='MET (Ainsworth)',
subject='Participant')
output = pg.rm_corr(data=df_lab,
x='estimation',
y='MET (Ainsworth)',
subject='Participant')
print(output)
print('\nGoogle Fit vs Ainsworth:')
g = pg.plot_rm_corr(data=df_lab,
x='MET (Google Fit)',
y='MET (Ainsworth)',
subject='Participant')
output = pg.rm_corr(data=df_lab,
x='MET (Google Fit)',
y='MET (Ainsworth)',
subject='Participant')
print(output)
print('\nWRIST vs ActiGraph VM3:')
g = pg.plot_rm_corr(data=df_lab,
x='estimation',
y='MET (VM3)',
subject='Participant')
output = pg.rm_corr(data=df_lab,
x='estimation',
y='MET (VM3)',
subject='Participant')
print(output)
print('\nIN-WILD:')
print('WRIST vs ActiGraph VM3:')
g = pg.plot_rm_corr(data=df_wild,
x='estimation',
y='MET (VM3)',
subject='Participant')
output = pg.rm_corr(data=df_wild,
x='estimation',
y='MET (VM3)',
subject='Participant')
print(output)
# load data into pandas dataframes
data_samples, data_class, data_images = load_data(
'./plots/experiment_results.pickl')
# with open('frames.pickl', 'wb') as f:
# pickle.dump((data_samples, data_class, data_images),f)
#with open('frames.pickl', 'rb') as f:
# data_samples, data_class, data_images = pickle.load(f)
print('\ncorrelation model uncertainty with error')
for dataset in data_class['dataset'].unique():
data_set = data_class[data_class['dataset'] == dataset]
for model in data_set['model'].unique():
model_data = data_set[data_set['model'] == model]
corr_res = pg.rm_corr(model_data,
x='correct',
y='model_uncertainty',
subject='image')
print(dataset + "/" + model, float(corr_res['r']),
float(corr_res['pval']))
print('\nged, p-values, each pair ged(model1) < ged(model2)')
for dataset in data_images['dataset'].unique():
data_set = data_images[data_images['dataset'] == dataset]
for modeli in data_set['model'].unique():
model_datai = data_set[data_set['model'] == modeli]
for modelj in data_set['model'].unique():
if modeli == modelj: continue
model_dataj = data_set[data_set['model'] == modelj]
ged_res = pg.ttest(model_datai['ged'],
model_dataj['ged'],