s151636/ium_151636
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

update script4.py

Browse Source
This commit is contained in:
Yevhenii Poliakov 2023-05-14 18:01:26 +02:00
parent bd09cb0dd1
commit 75381edb56
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
script4.py
View File

@ -5,7 +5,8 @@ from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler from sklearn.preprocessing import StandardScaler
# Step 1: Load the dataset # Step 1: Load the dataset
data = pd.read_csv('25k_movies.csv.shuf', error_bad_lines=False) data = pd.read_csv('25k_movies.csv.shuf')
# Step 2: Preprocess the data # Step 2: Preprocess the data
features = ['Total Run Time', 'User Rating', 'Genres', 'Director Name', 'Writer Name'] features = ['Total Run Time', 'User Rating', 'Genres', 'Director Name', 'Writer Name']
@ -16,7 +17,12 @@ data = data[features + [target]]
data = data.dropna() data = data.dropna()
# Filter out rows with a different number of columns # Filter out rows with a different number of columns
try:
data = data[data.apply(lambda x: len(x) == 12, axis=1)] data = data[data.apply(lambda x: len(x) == 12, axis=1)]
except pd.errors.ParserError as e:
print(f"Error occurred while parsing the dataset: {e}")
print("Dropping rows with inconsistent number of columns...")
data = data[data.apply(lambda x: len(x) == 12 if isinstance(x, list) else True, axis=1)]
# Convert categorical variables to numerical representations # Convert categorical variables to numerical representations
data = pd.get_dummies(data, columns=['Genres', 'Director Name', 'Writer Name']) data = pd.get_dummies(data, columns=['Genres', 'Director Name', 'Writer Name'])