Create 5_RealDataSetRegression.py

pages/5_RealDataSetRegression.py

@@ -0,0 +1,103 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+from matplotlib import pyplot as plt
+
+# Function to build the model
+def build_model(my_learning_rate):
+    model = tf.keras.models.Sequential()
+    model.add(tf.keras.layers.Dense(units=1, input_shape=(1,)))
+    model.compile(optimizer=tf.keras.optimizers.RMSprop(learning_rate=my_learning_rate),
+                  loss='mean_squared_error',
+                  metrics=[tf.keras.metrics.RootMeanSquaredError()])
+    return model
+
+# Function to train the model
+def train_model(model, df, feature, label, epochs, batch_size):
+    history = model.fit(x=df[feature], y=df[label], batch_size=batch_size, epochs=epochs)
+    trained_weight = model.get_weights()[0][0]
+    trained_bias = model.get_weights()[1]
+    epochs = history.epoch
+    hist = pd.DataFrame(history.history)
+    rmse = hist["root_mean_squared_error"]
+    return trained_weight, trained_bias, epochs, rmse
+
+# Function to plot the model
+def plot_the_model(trained_weight, trained_bias, feature, label, df):
+    plt.figure(figsize=(10, 6))
+    plt.xlabel(feature)
+    plt.ylabel(label)
+
+    random_examples = df.sample(n=200)
+    plt.scatter(random_examples[feature], random_examples[label])
+
+    x0 = 0
+    y0 = trained_bias
+    x1 = random_examples[feature].max()
+    y1 = trained_bias + (trained_weight * x1)
+    plt.plot([x0, x1], [y0, y1], c='r')
+
+    st.pyplot(plt)
+
+# Function to plot the loss curve
+def plot_the_loss_curve(epochs, rmse):
+    plt.figure(figsize=(10, 6))
+    plt.xlabel("Epoch")
+    plt.ylabel("Root Mean Squared Error")
+
+    plt.plot(epochs, rmse, label="Loss")
+    plt.legend()
+    plt.ylim([rmse.min()*0.97, rmse.max()])
+    st.pyplot(plt)
+
+# Load the dataset
+@st.cache
+def load_data():
+    url = "https://download.mlcc.google.com/mledu-datasets/california_housing_train.csv"
+    df = pd.read_csv(url)
+    df["median_house_value"] /= 1000.0
+    return df
+
+training_df = load_data()
+
+# Streamlit interface
+st.title("Simple Linear Regression with Real Data")
+
+if st.checkbox('Show raw data'):
+    st.write(training_df.head())
+
+learning_rate = st.sidebar.slider('Learning Rate', min_value=0.001, max_value=1.0, value=0.01, step=0.01)
+epochs = st.sidebar.slider('Epochs', min_value=1, max_value=1000, value=30, step=1)
+batch_size = st.sidebar.slider('Batch Size', min_value=1, max_value=len(training_df), value=30, step=1)
+feature = st.sidebar.selectbox('Select Feature', training_df.columns)
+label = 'median_house_value'
+
+if st.sidebar.button('Run'):
+    my_model = build_model(learning_rate)
+    weight, bias, epochs, rmse = train_model(my_model, training_df, feature, label, epochs, batch_size)
+
+    st.subheader('Model Plot')
+    plot_the_model(weight, bias, feature, label, training_df)
+
+    st.subheader('Loss Curve')
+    plot_the_loss_curve(epochs, rmse)
+
+# Function to make predictions
+def predict_house_values(n, feature, label):
+    batch = training_df[feature][10000:10000 + n]
+    predicted_values = my_model.predict_on_batch(x=batch)
+
+    st.write("feature   label          predicted")
+    st.write("  value   value          value")
+    st.write("          in thousand$   in thousand$")
+    st.write("--------------------------------------")
+    for i in range(n):
+        st.write("%5.0f %6.0f %15.0f" % (training_df[feature][10000 + i],
+                                        training_df[label][10000 + i],
+                                        predicted_values[i][0] ))
+
+n_predictions = st.sidebar.slider('Number of Predictions', min_value=1, max_value=100, value=10)
+if st.sidebar.button('Predict'):
+    st.subheader('Predictions')
+    predict_house_values(n_predictions, feature, label)