Spaces:
Sleeping
Sleeping
predictions
Browse files
app.py
CHANGED
|
@@ -15,11 +15,14 @@ from pr_featureEng import FeatureEngineeringPredict
|
|
| 15 |
from forecast_dataset import preprocess_function
|
| 16 |
from forecast_api import download_data
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
-
# Streamlit App Interface
|
| 20 |
-
st.title("O₃ and NO₂ forecast")
|
| 21 |
-
|
| 22 |
-
metric = st.selectbox("Select the metric for prediction", ["O₃", "NO₂"])
|
| 23 |
|
| 24 |
fitted_pcaO3 = pk.load(open("pcaO3.pkl",'rb'))
|
| 25 |
fitted_pcaNO2 = pk.load(open("pcaNO2.pkl",'rb'))
|
|
@@ -30,18 +33,9 @@ fitted_scalerNO2_features = pk.load(open("scalerNO2_features.pkl",'rb'))
|
|
| 30 |
fitted_scalerO3_targets = pk.load(open("scalerO3_targets.pkl",'rb'))
|
| 31 |
fitted_scalerNO2_targets = pk.load(open("scalerNO2_targets.pkl",'rb'))
|
| 32 |
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
"NO₂": "mlpNO2.keras"
|
| 36 |
-
}
|
| 37 |
|
| 38 |
-
# Model is cached to prevent reloading
|
| 39 |
-
@st.cache_resource()
|
| 40 |
-
def load_model(model_name):
|
| 41 |
-
|
| 42 |
-
model_dir = hf_hub_download(repo_id="senyakk/pollution_MLP", filename=model_name)
|
| 43 |
-
|
| 44 |
-
return tf.keras.models.load_model(model_dir)
|
| 45 |
|
| 46 |
def input_processing(data):
|
| 47 |
|
|
@@ -61,6 +55,7 @@ def input_processing(data):
|
|
| 61 |
|
| 62 |
return X_input
|
| 63 |
|
|
|
|
| 64 |
# Function to automatically refresh weather data and predictions every 6 hours
|
| 65 |
@st.cache_data(ttl=6*3600) # Cache data for 6 hours
|
| 66 |
def auto_update_data_and_prediction():
|
|
@@ -68,28 +63,31 @@ def auto_update_data_and_prediction():
|
|
| 68 |
data = download_data()
|
| 69 |
data = preprocess_function(data)
|
| 70 |
|
| 71 |
-
|
| 72 |
input_data = input_processing(data)
|
| 73 |
|
| 74 |
-
|
| 75 |
-
model = load_model(hf_map[metric])
|
| 76 |
-
|
| 77 |
# Make prediction
|
| 78 |
-
|
| 79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
-
# Round predictions
|
| 82 |
-
rounded_predictions = [round(pred, 2) for pred in prediction_flat]
|
| 83 |
|
| 84 |
# Create DataFrame for predictions
|
| 85 |
-
hours = np.arange(1, len(
|
| 86 |
-
prediction_df = pd.DataFrame({f"
|
| 87 |
|
| 88 |
# Save data and predictions
|
| 89 |
-
prediction_df.to_csv(f"data/prediction_{
|
| 90 |
|
| 91 |
return data, prediction_df
|
| 92 |
|
|
|
|
|
|
|
|
|
|
| 93 |
st.markdown("Below is the preprocessed data:")
|
| 94 |
data_placeholder = st.empty()
|
| 95 |
|
|
@@ -105,12 +103,18 @@ data_placeholder.write(hourly_dataframe)
|
|
| 105 |
# Plot predictions as a graph
|
| 106 |
st.write("Predicted values over time:")
|
| 107 |
fig, ax = plt.subplots()
|
| 108 |
-
ax.plot(prediction_df.index, prediction_df[f"
|
| 109 |
ax.set_xlabel('Hours')
|
| 110 |
-
ax.set_ylabel(f'
|
| 111 |
-
ax.set_title(f'
|
|
|
|
| 112 |
|
| 113 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
prediction_graph_placeholder.pyplot(fig)
|
| 115 |
|
| 116 |
# Option to display the table
|
|
|
|
| 15 |
from forecast_dataset import preprocess_function
|
| 16 |
from forecast_api import download_data
|
| 17 |
|
| 18 |
+
# Model is cached to prevent reloading
|
| 19 |
+
@st.cache_resource()
|
| 20 |
+
def load_model(model_name):
|
| 21 |
+
|
| 22 |
+
model_dir = hf_hub_download(repo_id="senyakk/pollution_MLP", filename=model_name)
|
| 23 |
+
|
| 24 |
+
return tf.keras.models.load_model(model_dir)
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
fitted_pcaO3 = pk.load(open("pcaO3.pkl",'rb'))
|
| 28 |
fitted_pcaNO2 = pk.load(open("pcaNO2.pkl",'rb'))
|
|
|
|
| 33 |
fitted_scalerO3_targets = pk.load(open("scalerO3_targets.pkl",'rb'))
|
| 34 |
fitted_scalerNO2_targets = pk.load(open("scalerNO2_targets.pkl",'rb'))
|
| 35 |
|
| 36 |
+
modelNO2 = load_model("mlpNO2.keras")
|
| 37 |
+
modelO3 = load_model("mlpO3.keras")
|
|
|
|
|
|
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
def input_processing(data):
|
| 41 |
|
|
|
|
| 55 |
|
| 56 |
return X_input
|
| 57 |
|
| 58 |
+
|
| 59 |
# Function to automatically refresh weather data and predictions every 6 hours
|
| 60 |
@st.cache_data(ttl=6*3600) # Cache data for 6 hours
|
| 61 |
def auto_update_data_and_prediction():
|
|
|
|
| 63 |
data = download_data()
|
| 64 |
data = preprocess_function(data)
|
| 65 |
|
|
|
|
| 66 |
input_data = input_processing(data)
|
| 67 |
|
|
|
|
|
|
|
|
|
|
| 68 |
# Make prediction
|
| 69 |
+
predictionO3 = modelO3.predict(input_data)
|
| 70 |
+
predictionO3_flat = predictionO3.flatten() # Flatten to 1D array
|
| 71 |
+
rounded_predictionsO3 = [round(pred, 2) for pred in predictionO3_flat]
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
predictionNO2 = modelNO2.predict(input_data)
|
| 75 |
+
predictionNO2_flat = predictionNO2.flatten() # Flatten to 1D array
|
| 76 |
+
rounded_predictionsNO2 = [round(pred, 2) for pred in predictionNO2_flat]
|
| 77 |
|
|
|
|
|
|
|
| 78 |
|
| 79 |
# Create DataFrame for predictions
|
| 80 |
+
hours = np.arange(1, len(predictionO3_flat) + 1)
|
| 81 |
+
prediction_df = pd.DataFrame({f"O3 Prediction": rounded_predictionsO3, "NO2 Prediction": rounded_predictionsNO2}, index=hours)
|
| 82 |
|
| 83 |
# Save data and predictions
|
| 84 |
+
prediction_df.to_csv(f"data/prediction_{datetime.now().strftime('%Y-%m-%d_%H-%M')}.csv", index=False)
|
| 85 |
|
| 86 |
return data, prediction_df
|
| 87 |
|
| 88 |
+
# Streamlit App Interface
|
| 89 |
+
st.title("O₃ and NO₂ forecast")
|
| 90 |
+
|
| 91 |
st.markdown("Below is the preprocessed data:")
|
| 92 |
data_placeholder = st.empty()
|
| 93 |
|
|
|
|
| 103 |
# Plot predictions as a graph
|
| 104 |
st.write("Predicted values over time:")
|
| 105 |
fig, ax = plt.subplots()
|
| 106 |
+
ax.plot(prediction_df.index, prediction_df[f"O3 Prediction"], marker='o', linestyle='-', color='b')
|
| 107 |
ax.set_xlabel('Hours')
|
| 108 |
+
ax.set_ylabel(f'O3 Prediction')
|
| 109 |
+
ax.set_title(f'O3 Prediction over Time')
|
| 110 |
+
prediction_graph_placeholder.pyplot(fig)
|
| 111 |
|
| 112 |
+
|
| 113 |
+
fig, ax = plt.subplots()
|
| 114 |
+
ax.plot(prediction_df.index, prediction_df[f"NO2 Prediction"], marker='o', linestyle='-', color='b')
|
| 115 |
+
ax.set_xlabel('Hours')
|
| 116 |
+
ax.set_ylabel(f'NO2 Prediction')
|
| 117 |
+
ax.set_title(f'NO2 Prediction over Time')
|
| 118 |
prediction_graph_placeholder.pyplot(fig)
|
| 119 |
|
| 120 |
# Option to display the table
|