plt.ylabel("Tags with quality under {} (%)".format(quality_top*100))
plt.tight_layout()
plt.legend([])
plt.show()
```
%% Output
%% Cell type:markdown id: tags:
In the cell above, you see the percentage of labels per body part which have a quality lower than the selected value (0.50 by default) **before** preprocessing. The values are taken directly from DeepLabCut.
%% Cell type:markdown id: tags:
### 3. Get coordinates, distances and angles
%% Cell type:markdown id: tags:
And get speed, acceleration and jerk for each
%% Cell type:code id: tags:
``` python
# Get coordinates, speeds, accelerations and jerks for positions
plt.title("Positions across time for centered data")
plt.legend(
fontsize=15,
bbox_to_anchor=(1.5,1),
title="Body part",
title_fontsize=18,
shadow=False,
facecolor="white",
)
plt.ylim(-100,60)
plt.xlim(-60,60)
plt.show()
```
%% Output
%% Cell type:markdown id: tags:
The figure above is a multi time-point scatter plot. The time_slider allows you to scroll across the video, and the length_slider selects the number of time-points to include. The idea is to intuitively visualize the data that goes into a training instance for a given preprocessing setting.