Chương 2_Bài tập số 5_Dùng PythonAI viết code dự đoán Số học và Data Visual giải Bingo18 trong Lý thuyết trò chơi
Bài tập 5: Dùng PythonAI viết code dự đoán Số học và Data Visual giải Bingo18 trong Lý thuyết trò chơi
https://vietlott.vn/vi/trung-thuong/ket-qua-trung-thuong/winning-number-bingo18
Sau khi copy/paste các dữ liệu vào Excel, CSV hoặc MS-SQL db
0 3;6;2
1 5;6;4
2 6;1;5
3 2;5;4
4 1;3;4
5 1;3;2
6 5;4;3
7 1;3;3
8 1;5;5
9 1;6;5
10 5;2;2
11 6;1;1
12 5;6;1
13 1;4;6
14 2;1;6
15 2;6;6
16 6;4;4
17 5;4;2
18 3;3;2
19 3;3;2
20 1;5;1
21 6;1;1
22 6;1;3
23 1;4;4
24 6;2;2
25 3;6;2
26 4;4;1
27 2;1;6
28 3;6;2
29 3;5;5
30 1;4;2
31 1;1;2
32 5;5;1
33 2;1;1
34 5;5;5
35 2;4;6
36 1;4;2
37 6;1;6
38 4;4;1
39 5;1;2
40 6;1;3
41 6;3;4
42 6;3;1
43 6;4;5
44 4;2;2
45 5;3;6
46 6;4;3
47 1;6;4
48 4;2;4
49 2;2;4
50 1;1;2
51 4;6;1
52 5;1;2
53 4;1;6
54 5;3;1
55 2;6;4
56 6;1;2
57 6;4;6
58 6;1;2
59 4;4;1
60 2;4;3
61 5;1;3
62 3;1;2
63 2;5;6
64 6;2;3
65 4;1;6
66 5;3;1
67 2;6;4
68 6;1;2
69 6;4;6
70 6;1;2
71 4;4;1
72 2;4;3
73 5;1;3
74 3;1;2
75 2;5;6
76 6;2;3
77 5;2;2
78 4;2;1
79 6;5;6
80 2;2;6
81 5;1;6
82 2;5;6
83 1;6;3
84 4;1;3
85 1;3;6
86 4;6;1
87 6;2;2
88 5;5;4
89 1;3;6
90 6;2;6
91 1;2;6
92 4;3;4
93 2;6;5
94 2;4;4Các hàm pd.read_csv
import numpy as np
import pandas as pd
#pd.__version__
import seaborn as sns
from matplotlib import pyplot as plt
from statsmodels.tsa.api import ExponentialSmoothing, SimpleExpSmoothing, Holt
from sklearn.linear_model import LinearRegression
import warnings
warnings.filterwarnings('ignore')
df = pd.read_csv(r"C:\Python311\workspaces\bingo18.csv")
pd.set_option("display.max_rows",df.shape[0]+1)
pd.set_option("display.max_columns",60)
df.shape
df# Import necessary libraries
import numpy as np
import tensorflow as tf
from tensorflow import keras
from keras import layers
from art import text2art
# Function to print the introduction of the program
def print_intro():
# Generate ASCII art with the text "LotteryAi"
ascii_art = text2art("Binggo 18 ball")
# Print the introduction and ASCII art
print("============================================================")
print("Source code Python AI: Le Toan Thang")
print("BTC: from poe.com>PythonChatAI")
print("ETH & BNB: Github.com/PhDLeToanThang/")
print("============================================================")
print(ascii_art)
print("Lottery prediction artificial intelligence")
# Function to load data from a file and preprocess it
def load_data():
# Load data from file, ignoring white spaces and accepting unlimited length numbers
data = np.genfromtxt('bingo18b.csv', delimiter=';', dtype=int)
# Replace all -1 values with 0
data[data == -1] = 0
# Split data into training and validation sets
train_data = data[:int(0.8*len(data))]
val_data = data[int(0.8*len(data)):]
# Get the maximum value in the data
max_value = np.max(data)
return train_data, val_data, max_value
# Function to create the model
def create_model(num_features, max_value):
# Create a sequential model
model = keras.Sequential()
# Add an Embedding layer, LSTM layer, and Dense layer to the model
model.add(layers.Embedding(input_dim=max_value+1, output_dim=64))
model.add(layers.LSTM(256))
model.add(layers.Dense(num_features, activation='softmax'))
# Compile the model with categorical crossentropy loss, adam optimizer, and accuracy metric
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
# Function to train the model
def train_model(model, train_data, val_data):
# Fit the model on the training data and validate on the validation data for 100 epochs
history = model.fit(train_data, train_data, validation_data=(val_data, val_data), epochs=100)
# Function to predict numbers using the trained model
def predict_numbers(model, val_data, num_features):
# Predict on the validation data using the model
predictions = model.predict(val_data)
# Get the indices of the top 'num_features' predictions for each sample in validation data
indices = np.argsort(predictions, axis=1)[:, -num_features:]
# Get the predicted numbers using these indices from validation data
predicted_numbers = np.take_along_axis(val_data, indices, axis=1)
return predicted_numbers
# Function to print the predicted numbers
def print_predicted_numbers(predicted_numbers):
# Print a separator line and "Predicted Numbers:"
print("============================================================")
print("Predicted Numbers:")
# Print only the first row of predicted numbers
print(', '.join(map(str, predicted_numbers[0])))
# Main function to run everything
def main():
# Print introduction of program
print_intro()
# Load and preprocess data
train_data, val_data, max_value = load_data()
# Get number of features from training data
num_features = train_data.shape[1]
# Create and compile model
model = create_model(num_features, max_value)
# Train model
train_model(model, train_data, val_data)
# Predict numbers using trained model
predicted_numbers = predict_numbers(model, val_data, num_features)
# Print predicted numbers
print_predicted_numbers(predicted_numbers)
# Run main function if this script is run directly (not imported as a module)
if __name__ == "__main__":
main()Màn kết quả:
============================================================ Predicted Numbers: 5, 6, 2
- Tiếp theo đặt cược hoặc theo dõi kết quả : Nhỏ, Hòa, Lớn