Commit Random Forest

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+import numpy as np
+import pickle
+
+# Cargar el modelo
+with open('model_rf.pkl', 'rb') as file:
+    rf = pickle.load(file)
+
+# Cargar el scaler
+with open('my-standard-scaler.pkl', 'rb') as file:
+    s_c = pickle.load(file)
+
+# Definir la función de predicción
+def predict(pH: float, EC: float, CCE: float, SOC: float, Sa: float, Si: float,
+            Cy: float, CEC: float, eCa: float, eMg: float, eK: float, eNa: float, eAlH: float):
+    ECEC = eCa + eMg + eK + eNa + eAlH
+    xCa = eCa/ECEC
+    xMg = eMg/ECEC
+    xK = eK/ECEC
+    xNa = eNa/ECEC
+    xAlH = eAlH/ECEC
+    BS1 = (eCa + eMg + eK + eNa)/CEC
+    BS2 = (eCa + eMg + eK + eNa)/ECEC
+    input_features = np.array([[pH,	EC,	CCE,	SOC,	Sa,	Si,	Cy,	CEC, ECEC,	xCa,	xMg,	xK,	xNa,	xAlH,	BS1,	BS2]])
+    input_features_scale = s_c.transform(input_features)
+    prediction = rf.predict(input_features_scale)[0].round(2)
+    return prediction
+
+# Crear la interfaz Gradio
+with gr.Blocks() as demo:
+    gr.Markdown("# Estima tu % de grasa corporal")
+    
+    pH = gr.Number(label="pH (--)", value=7.09, interactive=True)
+    EC = gr.Number(label="Ec (--)", value=0.31, interactive=True)
+    CCE = gr.Number(label="CCE (--)", value=0.20, interactive=True)
+    SOC = gr.Number(label="SOC (--)", value=2.9408, interactive=True)
+    Sa = gr.Number(label="Sa (--)", value=45.0, interactive=True)
+    Si = gr.Number(label="Si (--)", value=24.0, interactive=True)
+    Cy = gr.Number(label="Cy (--)", value=31.0, interactive=True)
+    CEC = gr.Number(label="CEC (--)", value=23.52, interactive=True)
+    eCa = gr.Number(label="eCa (--)", value=19.44, interactive=True)
+    eMg = gr.Number(label="eMg (--)", value=3.47, interactive=True)
+    eK = gr.Number(label="eK (--)", value=0.47, interactive=True)
+    eNa = gr.Number(label="eNa (--)", value=0.15, interactive=True)
+    eAlH = gr.Number(label="eAlH (--)", value=0.0, interactive=True)
+    
+    submit = gr.Button(value='Predecir')
+    output = gr.Textbox(label=": soil bulk density", interactive=False)
+    
+    submit.click(predict, inputs=[pH , EC, CCE, SOC, Sa, Si, Cy, CEC, eCa, eMg, eK, eNa, eAlH], outputs=[output])
+
+demo.launch(share=False, debug=False)

model_rf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6447c0b8d6e28cb88c221fe7b836c9347e5300b12b9bee415d4f3859e04c8744
+size 1015100

my-standard-scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51a9a34ac7cbc89634d5adfe4d525af82829399542167d08a88b66d21692e01
+size 1012

requirements.txt

@@ -0,0 +1,3 @@
+gradio==4.38.1
+numpy==1.24.3
+scikit-learn==1.2.2