Spaces:
Running
Running
Synced repo using 'sync_with_huggingface' Github Action
Browse files- __pycache__/dataset_wrangler.cpython-311.pyc +0 -0
- app.py +8 -6
- dataset_wrangler.py +6 -4
__pycache__/dataset_wrangler.cpython-311.pyc
ADDED
Binary file (5.99 kB). View file
|
|
app.py
CHANGED
@@ -4,9 +4,9 @@ import dataset_wrangler, image_analysis
|
|
4 |
|
5 |
dataset = "https://raw.githubusercontent.com/StateLibraryVictoria/public-domain-hack-2024/refs/heads/ch4-data-viz/datasets/ch3_colour_data_viz_suggestions_set_2_augmented.csv"
|
6 |
|
7 |
-
st.write(
|
8 |
-
|
9 |
-
)
|
10 |
|
11 |
palette_columns = ["pal_1", "pal_3", "pal_5"]
|
12 |
|
@@ -18,14 +18,17 @@ random_selection["iiif_url"] = random_selection["IE PID"].apply(
|
|
18 |
lambda x: image_analysis.get_iiif_image_urls(x)
|
19 |
)
|
20 |
|
21 |
-
for img in random_selection["iiif_url"].values.tolist():
|
22 |
-
|
23 |
|
24 |
|
25 |
df["created_year"] = df["Created - W 3 CDTF (DCTERMS)"].apply(
|
26 |
lambda x: dataset_wrangler.split_created_year(x)[0]
|
27 |
)
|
28 |
|
|
|
|
|
|
|
29 |
values = st.slider(
|
30 |
"Select a year range: ",
|
31 |
df["created_year"].min(),
|
@@ -33,7 +36,6 @@ values = st.slider(
|
|
33 |
(df["created_year"].min(), df["created_year"].max()),
|
34 |
)
|
35 |
|
36 |
-
# print(df["created_year"])
|
37 |
|
38 |
p = dataset_wrangler.create_grid(df)
|
39 |
|
|
|
4 |
|
5 |
dataset = "https://raw.githubusercontent.com/StateLibraryVictoria/public-domain-hack-2024/refs/heads/ch4-data-viz/datasets/ch3_colour_data_viz_suggestions_set_2_augmented.csv"
|
6 |
|
7 |
+
# st.write(
|
8 |
+
# "Scrambled Images from [https://www.slv.vic.gov.au/images](https://www.slv.vic.gov.au/images)"
|
9 |
+
# )
|
10 |
|
11 |
palette_columns = ["pal_1", "pal_3", "pal_5"]
|
12 |
|
|
|
18 |
lambda x: image_analysis.get_iiif_image_urls(x)
|
19 |
)
|
20 |
|
21 |
+
# for img in random_selection["iiif_url"].values.tolist():
|
22 |
+
# st.image(img)
|
23 |
|
24 |
|
25 |
df["created_year"] = df["Created - W 3 CDTF (DCTERMS)"].apply(
|
26 |
lambda x: dataset_wrangler.split_created_year(x)[0]
|
27 |
)
|
28 |
|
29 |
+
min_year = df["created_year"].min()
|
30 |
+
max_year = df["created_year"].max()
|
31 |
+
|
32 |
values = st.slider(
|
33 |
"Select a year range: ",
|
34 |
df["created_year"].min(),
|
|
|
36 |
(df["created_year"].min(), df["created_year"].max()),
|
37 |
)
|
38 |
|
|
|
39 |
|
40 |
p = dataset_wrangler.create_grid(df)
|
41 |
|
dataset_wrangler.py
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
import pandas as pd
|
2 |
import math
|
|
|
3 |
|
4 |
from bokeh.models import HoverTool
|
5 |
from bokeh.plotting import figure
|
@@ -8,11 +9,12 @@ from bokeh.models import CustomJS
|
|
8 |
|
9 |
def split_created_year(created_year):
|
10 |
|
11 |
-
|
12 |
-
start_date = split[0]
|
13 |
|
14 |
-
|
15 |
-
|
|
|
|
|
16 |
else:
|
17 |
end_date = start_date
|
18 |
|
|
|
1 |
import pandas as pd
|
2 |
import math
|
3 |
+
import re
|
4 |
|
5 |
from bokeh.models import HoverTool
|
6 |
from bokeh.plotting import figure
|
|
|
9 |
|
10 |
def split_created_year(created_year):
|
11 |
|
12 |
+
matches = re.findall("([1-3][0-9]{3})", created_year)
|
|
|
13 |
|
14 |
+
start_date = int(matches[0])
|
15 |
+
|
16 |
+
if len(matches) > 1:
|
17 |
+
end_date = int(matches[-1])
|
18 |
else:
|
19 |
end_date = start_date
|
20 |
|