Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
M
mooc-rr
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
3e6bf7b47a05a05ae3d6af86121dcb5d
mooc-rr
Compare Revisions
master...ff/post-soumission
Source
ff/post-soumission
Select Git revision
...
Target
master
Select Git revision
Compare
Commits (1)
Meilleur intervalle de confiance pour les prédictions
· 4c66a326
François Févotte
authored
Apr 17, 2020
4c66a326
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
82133 additions
and
80467 deletions
+82133
-80467
exercice.html
module3/exo3/exercice.html
+82118
-80458
exercice.jmd
module3/exo3/exercice.jmd
+15
-9
exercice.pdf
module3/exo3/exercice.pdf
+0
-0
No files found.
module3/exo3/exercice.html
View file @
4c66a326
This diff is collapsed.
Click to expand it.
module3/exo3/exercice.jmd
View file @
4c66a326
...
...
@@ -613,15 +613,15 @@ négligeable. L'incertitude sur $\beta$ est en particulier de nature à engendre
une perte de prédictibilité du modèle en temps long.
```julia; echo=false; results="
raw
"
data.theta_pred = predict(model, data)
pred = predict(model, data, interval=:prediction, level=0.95)
data.theta_pred = pred.prediction
data.theta_pred1 = pred.prediction .- pred.lower
data.theta_pred2 = pred.upper .- pred.prediction
plot(xlabel="
Date
", ylabel="
CO2
[
ppm
]
")
plot!(data_raw.date, data_raw.co2, label="
mesures
")
plot!(data.date, data.theta_pred, label="
mod
è
le
theta
", linewidth=3)
plot!(data.date, α .+ β1 * data.date_num .+ γ*data.date_num.^2,
linecolor="
red
", label="
mod
è
le
theta
(
IC
95
%
sur
beta
)
")
plot!(data.date, α .+ β2 * data.date_num .+ γ*data.date_num.^2,
linecolor="
red
", label=nothing)
plot!(data.date, data.theta_pred, label="
mod
è
le
theta
",
ribbon = (data.theta_pred1, data.theta_pred2))
disp()
```
...
...
@@ -654,7 +654,11 @@ Le modèle `GLM` précédemment calibré est utilisé pour prédire $\theta(t)$.
ajoute la fonction de forme annuelle $\phi(t)$ par périodicité.
```julia; results="
raw
"
prediction.theta = predict(model, prediction)
pred = predict(model, prediction, interval=:prediction, level=0.95)
prediction.theta = pred.prediction
prediction.theta1 = pred.prediction .- pred.lower
prediction.theta2 = pred.upper .- pred.prediction
prediction = join(prediction, avg, on=:day)
prediction.co2 = prediction.theta .+ prediction.phi_mean
...
...
@@ -670,8 +674,10 @@ d'extrapolation ; on observe un décalage significatif et croissant ensuite.
idx = data_raw.date .> Date(lastyear)
plot(xlabel="
Date
", ylabel="
CO2
[
ppm
]
")
plot!(data_raw.date[idx], data_raw.co2[idx], label="
mesures
")
plot!(prediction.date, prediction.theta, label="
tendance
", linewidth=2)
plot!(prediction.date, prediction.co2, label="
pr
é
diction
", linewidth=2)
plot!(prediction.date, prediction.theta, label="
tendance
",
linewidth=2,
ribbon = (prediction.theta1, prediction.theta2))
plot!(prediction.date, prediction.co2, label="
pr
é
diction
", linewidth=2)
disp()
```
...
...
module3/exo3/exercice.pdf
View file @
4c66a326
No preview for this file type