revert back

app.py

@@ -3,7 +3,7 @@ import hopsworks
 import joblib
 import pandas as pd
 import datetime
-from functions import get_weather_data_weekly, data_encoder, get_info
+from functions import get_weather_data_weekly, data_encoder, get_aplevel, get_color
 from PIL import Image
 
 
@@ -14,7 +14,7 @@ def fancy_header(text, font_size=24):
 st.set_page_config(layout="wide")
 st.title('Air Quality Prediction Project for Vienna! 🌩')
 vienna_image = Image.open('vienna.jpg')
-st.image(vienna_image, use_column_width='auto', caption='Vienna')
+st.image(vienna_image, use_column_width='auto')
 st.write(36 * "-")
 
 st.markdown("# This is a final project in the course ID2223 Scalable Machine Learning and Deep Learning :computer:")
@@ -49,7 +49,8 @@ fancy_header("Making AQI predictions for the next 7 days")
 
 preds = model.predict(data_encoder(weekly_data)).astype(int)
 
-color_level, poll_level = get_info(preds.reshape(1, -1))
+air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
+poll_level = get_aplevel(preds.T.reshape(-1, 1), air_pollution_level)
 
 next_week_datetime = [today + datetime.timedelta(days=d) for d in range(7)]
 next_week_str = [f"{days.strftime('%A')}, {days.strftime('%Y-%m-%d')}" for days in next_week_datetime]
@@ -57,6 +58,6 @@ next_week_str = [f"{days.strftime('%A')}, {days.strftime('%Y-%m-%d')}" for days
 df = pd.DataFrame(data=[preds, poll_level], index=["AQI", "Air pollution level"], columns=next_week_str)
 
 st.write("Here they are!")
-st.dataframe(df)
+st.dataframe(df.style.apply(get_color, subset=(["Air pollution level"], slice(None))))
 
 st.button("Re-run")

functions.py

@@ -172,9 +172,9 @@ def get_aplevel(temps:np.ndarray, table:list):
     level = [table[el] for el in cat[1]]
     return level
 
-def get_info(level:list):
-    air_pollution_level = {1:[50, 'Good', 'Green'], 2:[100, 'Moderate','Yellow'], 3:[150, 'Unhealthy for sensitive Groups','DarkOrange'],4:[200, 'Unhealthy','Red'] ,5:[300, 'Very Unhealthy','Purple'], 6:[1000, 'Hazardous','DarkRed']}
-    ind = [np.max(np.nonzero( el >= [air_pollution_level[key][0] for key in air_pollution_level.keys()])) for el in level]
-    color_text = [f"color:{air_pollution_level[idex][2]};" for idex in ind]
-    pollution_level = [air_pollution_level[idex][1] for idex in ind]
-    return color_text, pollution_level
+def get_color(level:list):
+    air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
+    color_list = ["Green", "Yellow", "DarkOrange", "Red", "Purple", "DarkRed"]
+    ind = [air_pollution_level.index(lel) for lel in level]
+    text = [f"color:{color_list[idex]};" for idex in ind]
+    return text