Spaces:
Sleeping
Sleeping
File size: 3,848 Bytes
64e86e0 2d51f4d 64e86e0 230669a 2d51f4d 64e86e0 2d51f4d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
import gradio as gr
# Define the mapping between user-friendly names and NASA variable names
data_mapping = {
"Temperature": {
"Earth Skin Temperature": "TS",
"Temperature at 2 Meters": "T2M",
"Wet Bulb Temperature at 2 Meters": "T2MWET"
},
"Moisture & Precipitation": {
"Precipitation Average": "PRECTOTCORR",
"Profile Soil Moisture (surface to bedrock)": "GWETPROF",
"Root Zone Soil Wetness (surface to 100 cm below)": "GWETROOT",
"Surface Soil Wetness (surface to 5 cm below)": "GWETTOP"
},
"Air & Pressure": {
"Specific Humidity at 2 Meters": "QV2M",
"Surface Pressure": "PS"
},
"Wind": {
"Wind Direction at 10 Meters": "WD10M",
"Wind Direction at 2 Meters": "WD2M",
"Wind Speed at 10 Meters": "WS10M",
"Wind Speed at 2 Meters": "WS2M"
}
}
def load_and_prepare_data():
data = pd.read_csv('data/preprocessed_data.csv')
nasa_features = [var for category in data_mapping.values() for var in category.values()]
target = 'Close_^FTSE'
X = data[nasa_features]
y = data[target]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, shuffle=False)
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
return X_train_scaled, X_test_scaled, y_train, y_test, scaler, nasa_features, data
def train_model(X_train_scaled, y_train):
model = LinearRegression()
model.fit(X_train_scaled, y_train)
return model
def create_prediction_interface(model, scaler, features_mapping, data):
def predict_func(*args):
input_values = pd.DataFrame([args], columns=nasa_features)
input_values_scaled = scaler.transform(input_values)
prediction = model.predict(input_values_scaled)
return f"${round(prediction[0], 2)} USD"
with gr.Blocks(theme=gr.themes.Default()) as demo:
gr.Markdown("### Stock Price Prediction")
gr.Markdown("Adjust NASA POWER DAS variables to see predicted stock prices.")
with gr.Row():
with gr.Column(scale=3):
gr.Markdown("#### Adjust Inputs")
inputs = []
for category, variables in features_mapping.items():
with gr.Accordion(category, open=False):
for csv_name, das_var in variables.items():
min_val = data[das_var].min()
max_val = data[das_var].max()
slider = gr.Slider(
label=csv_name,
minimum=min_val,
maximum=max_val,
value=(min_val + max_val) / 2,
step=(max_val - min_val) / 100
)
inputs.append(slider)
predict_btn = gr.Button("Predict", variant="primary")
with gr.Column(scale=1):
gr.Markdown("#### Predicted Result", elem_id="result-header")
output = gr.Textbox(label="Predicted Close_^FTSE", interactive=False, value="$0.00 USD")
predict_btn.click(fn=predict_func, inputs=inputs, outputs=output)
return demo
if __name__ == "__main__":
X_train_scaled, X_test_scaled, y_train, y_test, scaler, nasa_features, data = load_and_prepare_data()
model = train_model(X_train_scaled, y_train)
demo = create_prediction_interface(model, scaler, data_mapping, data)
demo.launch()
|