Skip to content

Feature pre process #26

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
YunliQi wants to merge 3 commits into
base: dev
Choose a base branch
from
Open

Feature pre process #26

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e28c9aa
Compare figure adjustment
YunliQi Feb 27, 2024
39b1718
Plot figure update
YunliQi Feb 27, 2024
778e26f
Flake 8
YunliQi Feb 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 13 additions & 7 deletions epios/post_process.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -428,29 +428,35 @@ def _compare(self, time_sample, gen_plot=False, scale_method: str = 'proportiona
'''
# Based on the input, use different scale method to estimate the true infection number
if scale_method == 'proportional':
result_scaled = np.array(self.result) * len(self.demo_data)
result_scaled = np.round(np.array(self.result) * len(self.demo_data))

# Get the true result from self.time_data
true_result = []
for t in time_sample:
true_result_plot = []
for t in range(max(time_sample) + 1):
num = self.time_data.iloc[t, 1:].value_counts().get(3, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(4, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(5, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(6, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(7, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(8, 0)
Comment on lines +435 to 441
Copy link

@KCGallagher KCGallagher Nov 12, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
for t in range(max(time_sample) + 1):
num = self.time_data.iloc[t, 1:].value_counts().get(3, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(4, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(5, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(6, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(7, 0)
num += self.time_data.iloc[t, 1:].value_counts().get(8, 0)
true_result_plot = [
sum(self.time_data.iloc[t, 1:].value_counts().get(i, 0) for i in range(3, 9))
for t in range(max(time_sample) + 1)
]

true_result.append(num)
true_result_plot.append(num)

true_result = []
for t in time_sample:
true_result.append(true_result_plot[t])

# Find the difference between estimated infection level and the real one
diff = np.array(true_result) - result_scaled
if gen_plot:
plt.figure()
plt.plot(time_sample, result_scaled, label='Predicted result', linestyle='--')
plt.plot(time_sample, true_result, label='True result')
plt.plot(range(max(time_sample) + 1), true_result_plot, label='True result')
plt.plot(time_sample, np.abs(diff), label='Absolute difference')
plt.legend()
plt.xlabel('Time')
plt.ylabel('Population')
plt.xlim(0, max(time_sample))
plt.ylim(0, len(self.demo_data))
plt.title('Number of infection in the population')
if saving_path_compare:
plt.savefig(saving_path_compare)
Expand Down Expand Up @@ -661,7 +667,7 @@ def _wrapper_Region_AgeRegion(self, sampling_method, sample_size, time_sample, n
# Plot the figure
if gen_plot:
plt.figure()
infected_population = np.array(infected_rate) * len(self.demo_data)
infected_population = np.round(np.array(infected_rate) * len(self.demo_data))
plt.plot(time_sample, infected_population)
plt.xlabel('Time')
plt.ylabel('Population')
Expand Down Expand Up @@ -748,7 +754,7 @@ def _wrapper_Age_Base(self, sampling_method, sample_size, time_sample,
# Plot the figure
if gen_plot:
plt.figure()
infected_population = np.array(infected_rate) * len(self.demo_data)
infected_population = np.round(np.array(infected_rate) * len(self.demo_data))
plt.plot(time_sample, infected_population)
plt.xlabel('Time')
plt.ylabel('Population')
Expand Down