In [1]:
# Import libraries. You may or may not use all of these.
!pip install -q git+https://github.com/tensorflow/docs
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split

try:
  # %tensorflow_version only exists in Colab.
  %tensorflow_version 2.x
except Exception:
  pass
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers

import tensorflow_docs as tfdocs
import tensorflow_docs.plots
import tensorflow_docs.modeling
In [2]:
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler
import requests
In [3]:
url = "https://cdn.freecodecamp.org/project-data/health-costs/insurance.csv"
filename = "insurance.csv"

# Using requests to fetch the content
response = requests.get(url)

if response.status_code == 200:
    with open(filename, 'wb') as file:
        file.write(response.content)
    print(f"Downloaded {filename} successfully.")
else:
    print(f"Failed to download {filename}. Status code: {response.status_code}")

# Read the dataset into a pandas DataFrame
dataset = pd.read_csv(filename)

# Display the last few rows of the DataFrame
dataset.tail()

Downloaded insurance.csv successfully.
Out[3]:
age sex bmi children smoker region expenses
1333 50 male 31.0 3 no northwest 10600.55
1334 18 female 31.9 0 no northeast 2205.98
1335 18 female 36.9 0 no southeast 1629.83
1336 21 female 25.8 0 no southwest 2007.95
1337 61 female 29.1 0 yes northwest 29141.36
In [4]:
X = dataset.drop('expenses', axis=1)  # Features
y = dataset['expenses']               # Target

X_encoded = pd.get_dummies(X, drop_first=True)

X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.2, random_state=42)

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

X_train_tensor = tf.convert_to_tensor(X_train, dtype=tf.float32)
X_test_tensor = tf.convert_to_tensor(X_test, dtype=tf.float32)
y_train_tensor = tf.convert_to_tensor(y_train, dtype=tf.float32)
y_test_tensor = tf.convert_to_tensor(y_test, dtype=tf.float32)

model = tf.keras.Sequential([
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1)  # Output layer
])

model.compile(optimizer='adam',
              loss='mean_squared_error',
              metrics=['mean_absolute_error', 'mean_squared_error'])

model.fit(X_train_tensor, y_train_tensor, epochs=100, verbose=1)

test_dataset = X_test_tensor
test_labels = y_test_tensor

Epoch 1/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 1s 785us/step - loss: 303127072.0000 - mean_absolute_error: 13045.2266 - mean_squared_error: 303127072.0000 
Epoch 2/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 328777088.0000 - mean_absolute_error: 13307.3828 - mean_squared_error: 328777088.0000
Epoch 3/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 320598304.0000 - mean_absolute_error: 13191.0605 - mean_squared_error: 320598304.0000
Epoch 4/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 290711264.0000 - mean_absolute_error: 11925.7725 - mean_squared_error: 290711264.0000
Epoch 5/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 680us/step - loss: 156425776.0000 - mean_absolute_error: 8095.3296 - mean_squared_error: 156425776.0000
Epoch 6/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 68558000.0000 - mean_absolute_error: 5201.1772 - mean_squared_error: 68558000.0000 
Epoch 7/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 665us/step - loss: 44595888.0000 - mean_absolute_error: 5144.8154 - mean_squared_error: 44595888.0000
Epoch 8/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 36456884.0000 - mean_absolute_error: 4529.2432 - mean_squared_error: 36456884.0000
Epoch 9/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 34498500.0000 - mean_absolute_error: 4278.2251 - mean_squared_error: 34498500.0000
Epoch 10/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 641us/step - loss: 32531668.0000 - mean_absolute_error: 4030.7861 - mean_squared_error: 32531668.0000
Epoch 11/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 31770378.0000 - mean_absolute_error: 4020.2729 - mean_squared_error: 31770378.0000
Epoch 12/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 36423320.0000 - mean_absolute_error: 4134.9868 - mean_squared_error: 36423320.0000
Epoch 13/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 32024830.0000 - mean_absolute_error: 3933.8020 - mean_squared_error: 32024830.0000
Epoch 14/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 34128172.0000 - mean_absolute_error: 3881.2820 - mean_squared_error: 34128172.0000
Epoch 15/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 636us/step - loss: 33951320.0000 - mean_absolute_error: 3878.2068 - mean_squared_error: 33951320.0000
Epoch 16/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 33179658.0000 - mean_absolute_error: 3873.3938 - mean_squared_error: 33179658.0000
Epoch 17/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 31634686.0000 - mean_absolute_error: 3780.1094 - mean_squared_error: 31634686.0000
Epoch 18/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 34470652.0000 - mean_absolute_error: 3892.7310 - mean_squared_error: 34470652.0000
Epoch 19/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 32617744.0000 - mean_absolute_error: 3852.7024 - mean_squared_error: 32617744.0000
Epoch 20/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 30902022.0000 - mean_absolute_error: 3652.2681 - mean_squared_error: 30902022.0000
Epoch 21/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 28247294.0000 - mean_absolute_error: 3506.6060 - mean_squared_error: 28247294.0000
Epoch 22/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 665us/step - loss: 29297368.0000 - mean_absolute_error: 3556.2395 - mean_squared_error: 29297368.0000
Epoch 23/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 29201058.0000 - mean_absolute_error: 3533.9326 - mean_squared_error: 29201058.0000
Epoch 24/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 26592116.0000 - mean_absolute_error: 3463.4758 - mean_squared_error: 26592116.0000
Epoch 25/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 650us/step - loss: 28331444.0000 - mean_absolute_error: 3532.1191 - mean_squared_error: 28331444.0000
Epoch 26/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 665us/step - loss: 31626366.0000 - mean_absolute_error: 3650.1870 - mean_squared_error: 31626366.0000
Epoch 27/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 31172814.0000 - mean_absolute_error: 3552.8535 - mean_squared_error: 31172814.0000
Epoch 28/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 28137976.0000 - mean_absolute_error: 3426.2104 - mean_squared_error: 28137976.0000
Epoch 29/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 664us/step - loss: 32137058.0000 - mean_absolute_error: 3587.0059 - mean_squared_error: 32137058.0000
Epoch 30/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 650us/step - loss: 27410294.0000 - mean_absolute_error: 3384.1179 - mean_squared_error: 27410294.0000
Epoch 31/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 695us/step - loss: 30338798.0000 - mean_absolute_error: 3528.2881 - mean_squared_error: 30338798.0000
Epoch 32/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 29469952.0000 - mean_absolute_error: 3444.7683 - mean_squared_error: 29469952.0000
Epoch 33/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 27269660.0000 - mean_absolute_error: 3316.7471 - mean_squared_error: 27269660.0000
Epoch 34/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 26628534.0000 - mean_absolute_error: 3267.7512 - mean_squared_error: 26628534.0000
Epoch 35/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 650us/step - loss: 25611450.0000 - mean_absolute_error: 3156.4065 - mean_squared_error: 25611450.0000
Epoch 36/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 27181080.0000 - mean_absolute_error: 3233.1938 - mean_squared_error: 27181080.0000
Epoch 37/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 27370384.0000 - mean_absolute_error: 3337.9441 - mean_squared_error: 27370384.0000
Epoch 38/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 28058864.0000 - mean_absolute_error: 3274.0164 - mean_squared_error: 28058864.0000
Epoch 39/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 26429112.0000 - mean_absolute_error: 3143.7629 - mean_squared_error: 26429112.0000
Epoch 40/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 28085334.0000 - mean_absolute_error: 3333.3010 - mean_squared_error: 28085334.0000
Epoch 41/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 27046620.0000 - mean_absolute_error: 3279.8252 - mean_squared_error: 27046620.0000
Epoch 42/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 26017076.0000 - mean_absolute_error: 3214.4004 - mean_squared_error: 26017076.0000
Epoch 43/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 620us/step - loss: 29189322.0000 - mean_absolute_error: 3389.2400 - mean_squared_error: 29189322.0000
Epoch 44/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 24580138.0000 - mean_absolute_error: 3119.8779 - mean_squared_error: 24580138.0000
Epoch 45/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 25856904.0000 - mean_absolute_error: 3149.4790 - mean_squared_error: 25856904.0000
Epoch 46/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 27137784.0000 - mean_absolute_error: 3315.7517 - mean_squared_error: 27137784.0000
Epoch 47/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 26736758.0000 - mean_absolute_error: 3136.1489 - mean_squared_error: 26736758.0000
Epoch 48/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 25663530.0000 - mean_absolute_error: 3169.4304 - mean_squared_error: 25663530.0000
Epoch 49/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 26738470.0000 - mean_absolute_error: 3303.2307 - mean_squared_error: 26738470.0000
Epoch 50/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 28136716.0000 - mean_absolute_error: 3259.9883 - mean_squared_error: 28136716.0000
Epoch 51/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 23884222.0000 - mean_absolute_error: 2944.8606 - mean_squared_error: 23884222.0000
Epoch 52/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 23388328.0000 - mean_absolute_error: 3031.6753 - mean_squared_error: 23388328.0000
Epoch 53/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 23986708.0000 - mean_absolute_error: 3072.8508 - mean_squared_error: 23986708.0000
Epoch 54/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 25174622.0000 - mean_absolute_error: 3157.4368 - mean_squared_error: 25174622.0000
Epoch 55/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 28057978.0000 - mean_absolute_error: 3216.5317 - mean_squared_error: 28057978.0000
Epoch 56/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 24624216.0000 - mean_absolute_error: 3089.2202 - mean_squared_error: 24624216.0000
Epoch 57/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 25120076.0000 - mean_absolute_error: 3072.4197 - mean_squared_error: 25120076.0000
Epoch 58/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 26444014.0000 - mean_absolute_error: 3074.5747 - mean_squared_error: 26444014.0000
Epoch 59/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 23882842.0000 - mean_absolute_error: 2902.6890 - mean_squared_error: 23882842.0000
Epoch 60/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 24066530.0000 - mean_absolute_error: 3018.1782 - mean_squared_error: 24066530.0000
Epoch 61/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 23464864.0000 - mean_absolute_error: 3082.0559 - mean_squared_error: 23464864.0000
Epoch 62/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 620us/step - loss: 24035530.0000 - mean_absolute_error: 3106.9731 - mean_squared_error: 24035530.0000
Epoch 63/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 25408576.0000 - mean_absolute_error: 3075.3896 - mean_squared_error: 25408576.0000
Epoch 64/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 21748542.0000 - mean_absolute_error: 2928.0640 - mean_squared_error: 21748542.0000
Epoch 65/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 650us/step - loss: 27040990.0000 - mean_absolute_error: 3131.2947 - mean_squared_error: 27040990.0000
Epoch 66/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 785us/step - loss: 23622348.0000 - mean_absolute_error: 2915.1575 - mean_squared_error: 23622348.0000
Epoch 67/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 25426632.0000 - mean_absolute_error: 3096.4429 - mean_squared_error: 25426632.0000
Epoch 68/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 21571290.0000 - mean_absolute_error: 2879.9998 - mean_squared_error: 21571290.0000
Epoch 69/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 22665574.0000 - mean_absolute_error: 2979.1418 - mean_squared_error: 22665574.0000
Epoch 70/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 22415434.0000 - mean_absolute_error: 2951.8030 - mean_squared_error: 22415434.0000
Epoch 71/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 25632196.0000 - mean_absolute_error: 3111.8918 - mean_squared_error: 25632196.0000
Epoch 72/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 19880604.0000 - mean_absolute_error: 2684.3992 - mean_squared_error: 19880604.0000
Epoch 73/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 25180318.0000 - mean_absolute_error: 3021.4487 - mean_squared_error: 25180318.0000
Epoch 74/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 23107894.0000 - mean_absolute_error: 2933.4749 - mean_squared_error: 23107894.0000
Epoch 75/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 24208788.0000 - mean_absolute_error: 2959.9321 - mean_squared_error: 24208788.0000
Epoch 76/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 24786800.0000 - mean_absolute_error: 3035.2725 - mean_squared_error: 24786800.0000
Epoch 77/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 23085632.0000 - mean_absolute_error: 2953.9124 - mean_squared_error: 23085632.0000
Epoch 78/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 27000622.0000 - mean_absolute_error: 3077.5002 - mean_squared_error: 27000622.0000
Epoch 79/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 21315088.0000 - mean_absolute_error: 2752.4597 - mean_squared_error: 21315088.0000
Epoch 80/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 22239062.0000 - mean_absolute_error: 2843.4739 - mean_squared_error: 22239062.0000
Epoch 81/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 589us/step - loss: 22670926.0000 - mean_absolute_error: 2897.5212 - mean_squared_error: 22670926.0000
Epoch 82/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 21948184.0000 - mean_absolute_error: 2821.6389 - mean_squared_error: 21948184.0000
Epoch 83/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 20042596.0000 - mean_absolute_error: 2746.9636 - mean_squared_error: 20042596.0000
Epoch 84/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 22196208.0000 - mean_absolute_error: 2951.8987 - mean_squared_error: 22196208.0000
Epoch 85/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 24866274.0000 - mean_absolute_error: 2944.3955 - mean_squared_error: 24866274.0000
Epoch 86/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 589us/step - loss: 22657618.0000 - mean_absolute_error: 2876.3962 - mean_squared_error: 22657618.0000
Epoch 87/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 25597148.0000 - mean_absolute_error: 3081.2859 - mean_squared_error: 25597148.0000
Epoch 88/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 20461942.0000 - mean_absolute_error: 2768.8005 - mean_squared_error: 20461942.0000
Epoch 89/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 23158618.0000 - mean_absolute_error: 2931.6836 - mean_squared_error: 23158618.0000
Epoch 90/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 23385888.0000 - mean_absolute_error: 2958.4143 - mean_squared_error: 23385888.0000
Epoch 91/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 19488660.0000 - mean_absolute_error: 2606.9434 - mean_squared_error: 19488660.0000
Epoch 92/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 19528246.0000 - mean_absolute_error: 2759.4492 - mean_squared_error: 19528246.0000
Epoch 93/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 23740142.0000 - mean_absolute_error: 3015.6807 - mean_squared_error: 23740142.0000
Epoch 94/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 618us/step - loss: 22508118.0000 - mean_absolute_error: 2886.6528 - mean_squared_error: 22508118.0000
Epoch 95/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 21910556.0000 - mean_absolute_error: 2750.7556 - mean_squared_error: 21910556.0000
Epoch 96/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 24056658.0000 - mean_absolute_error: 2852.9768 - mean_squared_error: 24056658.0000
Epoch 97/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 619us/step - loss: 21312070.0000 - mean_absolute_error: 2725.0603 - mean_squared_error: 21312070.0000
Epoch 98/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 604us/step - loss: 18899982.0000 - mean_absolute_error: 2657.1582 - mean_squared_error: 18899982.0000
Epoch 99/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 21564724.0000 - mean_absolute_error: 2817.8342 - mean_squared_error: 21564724.0000
Epoch 100/100
34/34 ━━━━━━━━━━━━━━━━━━━━ 0s 634us/step - loss: 21641074.0000 - mean_absolute_error: 2899.9607 - mean_squared_error: 21641074.0000
In [5]:
# RUN THIS CELL TO TEST YOUR MODEL. DO NOT MODIFY CONTENTS.
# Test model by checking how well the model generalizes using the test set.
loss, mae, mse = model.evaluate(test_dataset, test_labels, verbose=2)

print("Testing set Mean Abs Error: {:5.2f} expenses".format(mae))

if mae < 3500:
  print("You passed the challenge. Great job!")
else:
  print("The Mean Abs Error must be less than 3500. Keep trying.")

# Plot predictions.
test_predictions = model.predict(test_dataset).flatten()

a = plt.axes(aspect='equal')
plt.scatter(test_labels, test_predictions)
plt.xlabel('True values (expenses)')
plt.ylabel('Predictions (expenses)')
lims = [0, 50000]
plt.xlim(lims)
plt.ylim(lims)
_ = plt.plot(lims,lims)

9/9 - 0s - 9ms/step - loss: 20539132.0000 - mean_absolute_error: 2645.6421 - mean_squared_error: 20539132.0000
Testing set Mean Abs Error: 2645.64 expenses
You passed the challenge. Great job!
9/9 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step
In [ ]: