Spaces:
Sleeping
Sleeping
File size: 4,016 Bytes
c96b110 |
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 96 97 98 99 100 101 102 103 104 105 106 107 108 |
import gradio as gr
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
import joblib
from datetime import datetime
# Load and prepare data
df = pd.read_csv("water_potability (1).csv")
imputer = SimpleImputer(strategy='mean')
df_imputed = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
X = df_imputed.drop('Potability', axis=1)
y = df_imputed['Potability']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
# Metrics
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
feature_importance = pd.Series(model.feature_importances_, index=X.columns).sort_values(ascending=False)
def predict(ph, hardness, solids, chloramines, sulfate,
conductivity, organic_carbon, trihalomethanes, turbidity):
input_data = pd.DataFrame([[
ph, hardness, solids, chloramines, sulfate,
conductivity, organic_carbon, trihalomethanes, turbidity
]], columns=X.columns)
prediction = model.predict(input_data)[0]
label = "✅ Safe to Drink" if prediction == 1 else "❌ Not Safe to Drink"
proba = model.predict_proba(input_data)[0][prediction]
# --- Visuals ---
# Feature Importance
fig1, ax1 = plt.subplots(figsize=(6, 5))
feature_importance.plot(kind='barh', ax=ax1)
ax1.set_title("Feature Importance")
ax1.set_xlabel("Importance")
ax1.invert_yaxis()
# Class Distribution
fig2, ax2 = plt.subplots(figsize=(4, 4))
sns.countplot(x='Potability', data=df_imputed, ax=ax2)
ax2.set_title("Potability Class Distribution")
# Heatmap
fig3, ax3 = plt.subplots(figsize=(6, 5))
sns.heatmap(df_imputed.corr(), cmap='coolwarm', annot=False, ax=ax3)
ax3.set_title("Feature Correlation Heatmap")
# Metrics Text
metrics_info = (
f"📊 Model Performance on Test Set:\n\n"
f"- Accuracy : {accuracy:.2f}\n"
f"- Precision: {precision:.2f}\n"
f"- Recall : {recall:.2f}\n"
f"- F1 Score : {f1:.2f}\n\n"
f"Prediction Confidence: {proba:.2f}"
)
return f"{label}\n\n{metrics_info}", fig1, fig2, fig3
# Gradio Interface
with gr.Blocks() as demo:
gr.Markdown("# 💧 Trustworthy Water Quality Predictor")
gr.Markdown("Uses Random Forest with data imputation, performance metrics, and feature insights.")
with gr.Row():
with gr.Column():
ph = gr.Slider(0, 14, step=0.1, label="pH")
hardness = gr.Slider(50, 300, step=1, label="Hardness")
solids = gr.Slider(3000, 50000, step=100, label="Solids")
chloramines = gr.Slider(0, 15, step=0.1, label="Chloramines")
sulfate = gr.Slider(100, 500, step=1, label="Sulfate")
conductivity = gr.Slider(100, 800, step=1, label="Conductivity")
organic_carbon = gr.Slider(2, 30, step=0.1, label="Organic Carbon")
trihalomethanes = gr.Slider(0, 120, step=1, label="Trihalomethanes")
turbidity = gr.Slider(0, 7, step=0.1, label="Turbidity")
submit = gr.Button("Predict")
with gr.Column():
result = gr.Textbox(label="Prediction + Metrics")
fig1 = gr.Plot(label="Feature Importance")
fig2 = gr.Plot(label="Potability Class Distribution")
fig3 = gr.Plot(label="Correlation Heatmap")
submit.click(
fn=predict,
inputs=[ph, hardness, solids, chloramines, sulfate,
conductivity, organic_carbon, trihalomethanes, turbidity],
outputs=[result, fig1, fig2, fig3]
)
demo.launch()
|