import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.impute import SimpleImputer
# Function to load data from file
def load_data(file_path):
with open(file_path, 'r') as file:
data = np.array([[float(x) for x in line.split()] for line in file])
return data
# Load data from each feature file
feature_files = [
'mfeat-fou', 'mfeat-fac', 'mfeat-kar',
'mfeat-pix', 'mfeat-zer', 'mfeat-mor'
]
feature_data = [load_data(file) for file in feature_files]
# Concatenating training features from all 6 types
train_features = np.concatenate(feature_data, axis=1)
# Splitting the data into 1000 training examples and 1000 test examples
train_features, test_features, train_labels, test_labels = train_test_split(
train_features, np.repeat(np.arange(10), 200), test_size=1000, train_size=1000,
stratify=np.repeat(np.arange(10), 200), random_state=42
)
# Splitting the test set into the first 3 features and the last 3 features
test_features_part, test_features_missing = np.split(test_features, [356], axis=1)
print(np.shape(test_features_part))
print(np.shape(test_features_missing))
# Fit imputer on training data for the identified features
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
imputer.fit(train_features)
# Fit on the last 3 feature types
# Impute missing values only for the identified features in the test set
test_features_missing = matrix_with_nan = np.full(test_features_missing.shape,
np.nan)
test_features_combined = np.concatenate((test_features_part,
test_features_missing), axis=1)
test_features_imputer = imputer.transform(test_features_combined)
# Train a classifier on the training set with all available features
clf = RandomForestClassifier(n_estimators=100, random_state=42)
clf.fit(train_features, train_labels)
# Evaluate accuracy on the test set
predictions = clf.predict(test_features_imputer)
accuracy = accuracy_score(test_labels, predictions)
# Display the accuracy
print(f"Imputation accuracy using mean strategy: {accuracy:.4f}")
