This commit is contained in:
Yevhenii Poliakov 2023-05-14 21:11:40 +02:00
parent ca4fe6932b
commit c3c751076e
2 changed files with 51 additions and 2 deletions

View File

@ -39,9 +39,9 @@ pipeline {
echo("run data script")
//sh "source docker_ium/bin/activate"
sh "ls -a"
sh "chmod u+x script5.py"
sh "chmod u+x script5_1.py"
//sh "pip3 show pandas"
sh "python3 script5.py"
sh "python3 script5_1.py"
}
}

49
script5_1.py Normal file
View File

@ -0,0 +1,49 @@
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MultiLabelBinarizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam
# Load the dataset from the CSV file
data = pd.read_csv('data.csv', on_bad_lines='skip', engine='python')
# Prepare the data
X = data[['movie title', 'User Rating', 'Director', 'Top 5 Casts', 'Writer', 'year']]
y = data['Rating']
# Preprocess the data
# Convert the categorical columns into numerical representations
mlb_genres = MultiLabelBinarizer()
X_genres = mlb_genres.fit_transform(data['Generes'])
X.loc[:, 'Generes'] = X_genres.tolist()
mlb_keywords = MultiLabelBinarizer()
X_keywords = mlb_keywords.fit_transform(data['Plot Kyeword'])
X.loc[:, 'Plot Kyeword'] = X_keywords.tolist()
mlb_casts = MultiLabelBinarizer()
X_casts = mlb_casts.fit_transform(data['Top 5 Casts'].astype(str))
X.loc[:, 'Top 5 Casts'] = X_casts.tolist()
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create the neural network model
model = Sequential()
model.add(Dense(32, activation='relu', input_dim=X.shape[1]))
model.add(Dense(16, activation='relu'))
model.add(Dense(1))
# Compile the model
model.compile(optimizer=Adam(), loss='mse')
# Train the model
model.fit(X_train, y_train, batch_size=64, epochs=10, validation_data=(X_test, y_test))
# Evaluate the model
mse = model.evaluate(X_test, y_test)
print("Mean Squared Error:", mse)