Explanation: This is a machine learning practical project (with data + code + documentation + video explanation). If you need data + code + documentation + video explanation, you can go directly to the end of the article to get it.
1. Project background
Ant Colony Optimization (ACO) is a new bionic evolutionary algorithm derived from the natural biological world, adopted by Italian scholars M. Dorigo, V. Maniezzo and A. Colorni in the early 1990s. A population-based heuristic random search algorithm that simulates the collective path-finding behavior of ants in nature”. Ants have the ability to find the shortest path from the nest to the food source without any prompts, and can change with the environment, Adaptively search for new paths and produce new choices. The fundamental reason is that when ants are looking for food, they can release a special secretion-pheromone (also known as pheromone) on the path they walk, and then As time goes by, the substance will gradually volatilize, and the probability that the subsequent ants choose this path is proportional to the intensity of the pheromone on this path at that time. When more and more ants pass through a path, the pheromone left by it will also More and more, the probability of ants choosing this path is higher, which increases the intensity of pheromone on this path. And the pheromone with high intensity will attract more ants, thus forming a positive feedback mechanism. Through this positive feedback mechanism, ants can eventually find the shortest path.
This project uses the ACO ant colony optimization algorithm to find the optimal parameter value to optimize the random forest classification model.
2. Data acquisition
The modeling data for this time comes from the Internet (compiled by the author of this project), and the statistics of the data items are as follows:
The data details are as follows (partial display):
3. Data preprocessing
3.1 View data with Pandas tools
Use the head() method of the Pandas tool to view the first five rows of data:
key code:
3.2 View missing data
Use the info() method of the Pandas tool to view data information:
As can be seen from the above figure, there are a total of 11 variables, and there are no missing values in the data, with a total of 1000 data.
key code:
3.3 Data descriptive statistics
Use the describe() method of the Pandas tool to view the mean, standard deviation, minimum, quantile, and maximum of the data.
The key code is as follows:
4. Exploratory data analysis
4.1 y variable histogram
Use the plot() method of the Matplotlib tool to draw a histogram:
4.2 y=1 sample x1 variable distribution histogram
Use the hist() method of the Matplotlib tool to draw a histogram:
4.3 Correlation Analysis
As can be seen from the figure above, the larger the value, the stronger the correlation. A positive value is a positive correlation, and a negative value is a negative correlation.
5. Feature engineering
5.1 Create feature data and label data
The key code is as follows:
5.2 Dataset Split
Use the train_test_split() method to divide according to 80% training set and 20% test set. The key code is as follows:
6. Construct ACO ant colony optimization algorithm to optimize random forest classification model
Mainly use the ACO ant colony optimization algorithm to optimize the random forest classification algorithm for target classification.
6.1 Optimal parameters for ACO ant colony optimization algorithm
key code:
Optimal parameters:
6.2 Optimal parameter value construction model
6.2 Optimal parameter value construction model 
7. Model evaluation
7.1 Evaluation indicators and results
Evaluation indicators mainly include accuracy rate, precision rate, recall rate, F1 score and so on.
It can be seen from the above table that the F1 score is 0.9050, indicating that the model works well.
The key code is as follows:
7.2 Classification report
As can be seen from the above figure, the F1 score of classification 0 is 0.90; the F1 score of classification 1 is 0.91.
7.3 Confusion Matrix
As can be seen from the above figure, there are 9 samples that are actually 0 and predicted to be not 0; there are 10 samples that are actually 1 and predicted to be not 1, and the overall prediction accuracy is good.
8. Conclusion and prospect
To sum up, this paper uses the ACO ant colony optimization algorithm to find the optimal parameter value of the random forest classification algorithm to build a classification model, and finally proves that the model we proposed works well. This model can be used for forecasting of everyday products.
# ====Define penalty item function======
def calc_e(X):
"""Calculate the penalty term of ants, the dimension of X is size * 2 """
ee = 0
"""Calculate the penalty for the first constraint"""
e1 = X[0] + X[1] - 6
ee + = max(0, e1)
"""Calculate the penalty for the second constraint"""
e2 = 3 * X[0] - 2 * X[1] - 5
ee + = max(0, e2)
return ee
# *************************************************** *******************************
# The materials required for the actual combat of this machine learning project, the project resources are as follows:
# project instruction:
# Link: https://pan.baidu.com/s/1c6mQ_1YaDINFEttQymp2UQ
# Extract code: thgk
# *************************************************** *******************************
# ===Define the selection operation function between children and parents====
def update_best(parent, parent_fitness, parent_e, child, child_fitness, child_e, X_train, X_test, y_train, y_test):
"""
For different problems, the threshold of the penalty item is reasonably selected. In this example the threshold is 0.1
:param parent: parent individual
:param parent_fitness: parent fitness value
:param parent_e : parent penalty item
:param child: child individual
:param child_fitness child fitness value
:param child_e : child penalty item
:return: The better of parent and offspring, fitness, penalty
"""
if abs(parent[0]) > 0: # Judgment value
max_depth = int(abs(parent[0])) + 2 # assignment
else:
max_depth = int(abs(parent[0])) + 5 # assignment
if abs(parent[1]) > 0: # Judgment value
min_samples_leaf = int(abs(parent[1])) + 1 # assignment
else:
min_samples_leaf = int(abs(parent[1])) + 5 # assignment
For more project practice, see the list of machine learning project practice collections:
List of actual combat collections of machine learning projects