import time
import csv as csv
import sys
from sklearn import metrics
from sklearn.cross_validation import ShuffleSplit
from sklearn.grid_search import RandomizedSearchCV, GridSearchCV
from sklearn.linear_model import SGDClassifier
from operator import itemgetter
# Script
###################################
if __name__ == '__main__':
# Do all the feature engineering
print "Generating initial training/test sets"
input_df, submit_df = loaddata.getDataSets(raw=False,
binary=True,
bins=False,
scaled=True)
# Collect the test data's PassengerIds then drop it from the train and test sets
submit_ids = submit_df['PassengerId']
input_df.drop(['PassengerId'], axis=1, inplace=1)
submit_df.drop(['PassengerId'], axis=1, inplace=1)
# Run dimensionality reduction and clustering on the remaining feature set. This will return an unlabeled
# set of derived parameters along with the ClusterID so we can train multiple models for different groups
print "Dimensionality Reduction and Clustering..."
input_df, submit_df = loaddata.reduceAndCluster(input_df, submit_df, 2)
# Add the passenger ID back into the test set so we can keep track of them as we train different models
submit_df = pd.concat([submit_ids, submit_df], axis=1)
print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
score.mean_validation_score,
np.std(score.cv_validation_scores)))
print("Parameters: {0}".format(score.parameters))
print("")
if params == None:
params = score.parameters
return params
# Script
###################################
input_df, submit_df = loaddata.getDataSets(bins=False, scaled=True, raw=False)
# Collect the test data's PassengerIds
ids = submit_df['PassengerId'].values
# Remove variables that we couldn't transform into features:
drop_list = ['PassengerId']
input_df.drop(drop_list, axis=1, inplace=1)
submit_df.drop(drop_list, axis=1, inplace=1)
submit_df.drop('Survived', axis=1, inplace=1)
print 'Building Naive Bayes Classifier with ' + str(len(input_df.columns)) \
+ ' columns: ' + str(list(input_df.columns.values))
train_data = input_df.values
X = train_data[0::,1::]
Custom scoring function for hyperparameter optimization. In this case, we want to print out the oob score
"""
score = estimator.oob_score_
print "oob_score_:", score
return score
if __name__ == '__main__':
"""
Main script, this contains logic to execute the full pipeline to generate a RandomForest for the titanic data
"""
##############################################################################################################
# Prepare data for pipeline
#
print "\nGenerating initial training/test sets"
input_df, submit_df = loaddata.getDataSets(bins=True, scaled=True, binary=True)
# Collect the test data's PassengerIds then drop it from the train and test sets
submit_ids = submit_df['PassengerId']
input_df.drop('PassengerId', axis=1, inplace=1)
submit_df.drop('PassengerId', axis=1, inplace=1)
features_list = input_df.columns.values[1::] # Save for feature importance graph
X = input_df.values[:, 1::]
y = input_df.values[:, 0]
# Set the weights to adjust for uneven class distributions (fewer passengers survived than died)
survived_weight = .75
y_weights = np.array([survived_weight if s == 1 else 1 for s in y])
print("")
if params == None:
params = score.parameters
return params
# Script
###################################
if __name__ == '__main__':
# Do all the feature engineering
input_df, submit_df = loaddata.getDataSets(raw=False, binary=True, bins=False)
submit_df.drop('Survived', axis=1, inplace=1)
print 'All generated features: ' + str(list(input_df.columns.values))
# Collect the test data's PassengerIds
ids = submit_df['PassengerId'].values
# Remove variables that aren't appropriate for this model:
drop_list = ['PassengerId']
input_df.drop(drop_list, axis=1, inplace=1)
submit_df.drop(drop_list, axis=1, inplace=1)
print 'Building SVC with ', len(input_df.columns), ' columns: ', list(input_df.columns.values)
print "Number of training examples: ", input_df.shape[0]
import sys
import re
from sklearn import cross_validation
from sklearn.grid_search import GridSearchCV
from sklearn.grid_search import RandomizedSearchCV
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import RandomForestClassifier
from operator import itemgetter
# Script
###################################
if __name__ == '__main__':
# Do all the feature engineering
print "Generating initial training/test sets"
input_df, submit_df = loaddata.getDataSets(raw=False, binary=True, bins=False, scaled=True, balanced=True)
# Collect the test data's PassengerIds then drop it from the train and test sets
submit_ids = submit_df['PassengerId']
input_df.drop(['PassengerId'], axis=1, inplace=1)
submit_df.drop(['PassengerId'], axis=1, inplace=1)
# Run dimensionality reduction and clustering on the remaining feature set. This will return an unlabeled
# set of derived parameters along with the ClusterID so we can train multiple models for different groups
print "Dimensionality Reduction and Clustering..."
input_df, submit_df = loaddata.reduceAndCluster(input_df, submit_df, 2)
# Add the passenger ID back into the test set so we can keep track of them as we train different models
submit_df = pd.concat([submit_ids, submit_df], axis=1)
print 'Generated', input_df.columns.size, 'features:', input_df.columns.values
print 'ROC AUC: %0.2f' % roc_auc
if plot:
# Plot of a ROC curve for a specific class
plt.figure()
plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curve')
plt.legend(loc="lower right")
plt.show()
return roc_auc
if __name__ == "__main__":
"""
Test method
"""
print "Testing ROC Curve..."
input_df, _ = loaddata.getDataSets(bins=True, scaled=True, binary=True)
input_df.drop("PassengerId", axis=1, inplace=True)
X = input_df.values[:, 1::]
y = input_df.values[:, 0]
forest = RandomForestClassifier(n_estimators=10000, n_jobs=-1)
generate_roc_curve(forest, X, y)
print("Model with rank: {0}".format(i + 1))
print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
score.mean_validation_score, np.std(score.cv_validation_scores)))
print("Parameters: {0}".format(score.parameters))
print("")
if params == None:
params = score.parameters
return params
# Script
###################################
input_df, submit_df = loaddata.getDataSets(bins=False, scaled=False, raw=False)
# Collect the test data's PassengerIds
ids = submit_df['PassengerId'].values
# Remove variables that we couldn't transform into features:
drop_list = ['PassengerId']
input_df.drop(drop_list, axis=1, inplace=1)
submit_df.drop(drop_list, axis=1, inplace=1)
submit_df.drop('Survived', axis=1, inplace=1)
print 'Building Naive Bayes Classifier with ' + str(len(input_df.columns)) \
+ ' columns: ' + str(list(input_df.columns.values))
train_data = input_df.values
X = train_data[0::, 1::]