Predicting traffic using Extremely Random Forest regressor

In order to predict traffic using Extremely Random Forest regressor I'll use the dataset available at:
https://archive.ics.uci.edu/ml/datasets/Dodgers+Loop+Sensor. This dataset consists of data that counts the number of vehicles passing by on the road during baseball games played at Los Angeles Dodgers stadium. In order to make the data readily available for analysis, we need to pre-process it. The pre-processed data is in the file traffic_data.txt. In this file, each line contains comma-separated strings. Let's take the first line as an example:

Tuesday,00:00,San Francisco,no,3

With reference to the preceding line, it is formatted as follows:

Day of the week, time of the day, opponent team, binary value indicating whether or not a baseball game is currently going on (yes/no), number of vehicles passing by.

Our goal is to predict the number of vehicles going by using the given information. Since the output variable is continuous valued, we need to build a regressor that can predict the output. We will be using Extremely Random Forests to build this regressor in the program shown below:

import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report, mean_absolute_error
from sklearn import preprocessing
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split

# Load input data
input_file = 'traffic_data.txt'
data = []
with open(input_file, 'r') as f:
    for line in f.readlines():
        items = line[:-1].split(',')
        data.append(items)

data = np.array(data)

# Convert string data to numerical data
label_encoder = []
X_encoded = np.empty(data.shape)
for i, item in enumerate(data[0]):
    if item.isdigit():
        X_encoded[:, i] = data[:, i]
    else:
        label_encoder.append(preprocessing.LabelEncoder())
        X_encoded[:, i] = label_encoder[-1].fit_transform(data[:, i])

X = X_encoded[:, :-1].astype(int)
y = X_encoded[:, -1].astype(int)

# Split data into training and testing datasets
X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.25, random_state=5)

# Extremely Random Forests regressor
params = {'n_estimators': 100, 'max_depth': 4, 'random_state': 0}
regressor = ExtraTreesRegressor(**params)
regressor.fit(X_train, y_train)

# Compute the regressor performance on test data
y_pred = regressor.predict(X_test)
print("Mean absolute error:", round(mean_absolute_error(y_test, y_pred), 2))

# Testing encoding on single data instance
test_datapoint = ['Saturday', '10:20', 'Atlanta', 'no']
test_datapoint_encoded = [-1] * len(test_datapoint)
count = 0
for i, item in enumerate(test_datapoint):
    if item.isdigit():
        test_datapoint_encoded[i] = int(test_datapoint[i])
    else:
       
        test_datapoint_encoded[i] = int(label_encoder[i].transform([test_datapoint[i]]))
        count = count + 1

test_datapoint_encoded = np.array(test_datapoint_encoded)

# Predict the output for the test datapoint
print("Predicted traffic:", int(regressor.predict([test_datapoint_encoded])[0]))



After importing the required packages we load data in the file traffic_data.txt:

input_file = 'traffic_data.txt'
data = []
with open(input_file, 'r') as f:
    for line in f.readlines():
        items = line[:-1].split(',')
        data.append(items)

data = np.array(data)

Next we create label encoders as we need to encode the non-numerical features in the data. We also need to ensure that we don't encode numerical features. Each feature that needs to be encoded needs to have a separate label encoder. We need to keep track of these encoders because we will need them
when we want to compute the output for an unknown data point.

label_encoder = []
X_encoded = np.empty(data.shape)
for i, item in enumerate(data[0]):
    if item.isdigit():
        X_encoded[:, i] = data[:, i]
    else:
        label_encoder.append(preprocessing.LabelEncoder())
        X_encoded[:, i] = label_encoder[-1].fit_transform(data[:, i])

X = X_encoded[:, :-1].astype(int)
y = X_encoded[:, -1].astype(int)

Now we split data into training and testing datasets then train an extremely Random Forests regressor:

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=5)

params = {'n_estimators': 100, 'max_depth': 4, 'random_state': 0}
regressor = ExtraTreesRegressor(**params)
regressor.fit(X_train, y_train)

In the next step we compute the performance of the regressor on testing data:

y_pred = regressor.predict(X_test)
print("Mean absolute error:", round(mean_absolute_error(y_test, y_pred), 2))


Now we compute the output for an unknown data point. We will be using those label encoders to convert non-numerical features into numerical values:

test_datapoint = ['Saturday', '10:20', 'Atlanta', 'no']
test_datapoint_encoded = [-1] * len(test_datapoint)
count = 0
for i, item in enumerate(test_datapoint):
    if item.isdigit():
        test_datapoint_encoded[i] = int(test_datapoint[i])
    else:
       
        test_datapoint_encoded[i] = int(label_encoder[i].transform([test_datapoint[i]]))
        count = count + 1

test_datapoint_encoded = np.array(test_datapoint_encoded)

Finally we predict the output for the test datapoint:

print("Predicted traffic:", int(regressor.predict([test_datapoint_encoded])[0]))

The output of the program is shown below:

Mean absolute error: 7.42
Predicted traffic: 26
------------------
(program exited with code: 0)

Press any key to continue . . .

The Predicted traffic is 26 which is pretty close to the actual value. You can confirm this from the data file.