Classifying survivors in Titanic
The customary binary classification problem for people who want to start with Machine learning.
Introduction:
Kaggle has created a number of competitions designed for beginners. The most popular of these competitions, and the one we’ll be looking at, is about predicting which passengers survived the sinking of the Titanic. If you are a beginner in data science you probably have already heard about this. We will be understanding on how to use different ML techniques, choosing the best performing model, then optimising the best performing model further to improve our predictions. Let’s get started
Importing Libraries:
Importing libraries
# linear algebra
import numpy as np
# data processing
import pandas as pd
# data visualization
import seaborn as sns
%matplotlib inline
from matplotlib import pyplot as plt
from matplotlib import style
# Algorithms
from sklearn import linear_model
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC, LinearSVC
from sklearn.naive_bayes import GaussianNB
Pulling Data into python
Pulling data
test_df = pd.read_csv("test.csv")
train_df = pd.read_csv("train.csv")
EDA (Exploratory Data Analysis)
Understanding the data we are dealing with.
train_df.info()
train_df.head(8)
Calculating the missing Data
total = train_df.isnull().sum().sort_values(ascending=False)
percent_1 = train_df.isnull().sum()/train_df.isnull().count()*100
percent_2 = (round(percent_1, 1)).sort_values(ascending=False)
missing_data = pd.concat([total, percent_2], axis=1, keys=['Total', '%'])
missing_data.head(5)
Understanding survivor ratio between male and female
survived = 'survived'
not_survived = 'not survived'
fig, axes = plt.subplots(nrows=1, ncols=2,figsize=(10, 4))
women = train_df[train_df['Sex']=='female']
men = train_df[train_df['Sex']=='male']
ax = sns.distplot(women[women['Survived']==1].Age.dropna(), bins=18, label = survived, ax = axes[0], kde =False)
ax = sns.distplot(women[women['Survived']==0].Age.dropna(), bins=40, label = not_survived, ax = axes[0], kde =False)
ax.legend()
ax.set_title('Female')
ax = sns.distplot(men[men['Survived']==1].Age.dropna(), bins=18, label = survived, ax = axes[1], kde = False)
ax = sns.distplot(men[men['Survived']==0].Age.dropna(), bins=40, label = not_survived, ax = axes[1], kde = False)
ax.legend()
_ = ax.set_title('Male')
Preprocessing the Data
1. Age
Adding random values based on the means and Standard deviation of the non missing values in the column.
data = [train_df, test_df]
for dataset in data:
mean = train_df["Age"].mean()
std = test_df["Age"].std()
is_null = dataset["Age"].isnull().sum()
# compute random numbers between the mean, std and is_null
rand_age = np.random.randint(mean - std, mean + std, size = is_null)
# fill NaN values in Age column with random values generated
age_slice = dataset["Age"].copy()
age_slice[np.isnan(age_slice)] = rand_age
dataset["Age"] = age_slice
dataset["Age"] = train_df["Age"].astype(int)
train_df["Age"].isnull().sum()
2. Bucketing Age
data = [train_df, test_df]
for dataset in data:
dataset['Age'] = dataset['Age'].astype(int)
dataset.loc[ dataset['Age'] <= 11, 'Age'] = 0
dataset.loc[(dataset['Age'] > 11) & (dataset['Age'] <= 18), 'Age'] = 1
dataset.loc[(dataset['Age'] > 18) & (dataset['Age'] <= 22), 'Age'] = 2
dataset.loc[(dataset['Age'] > 22) & (dataset['Age'] <= 27), 'Age'] = 3
dataset.loc[(dataset['Age'] > 27) & (dataset['Age'] <= 33), 'Age'] = 4
dataset.loc[(dataset['Age'] > 33) & (dataset['Age'] <= 40), 'Age'] = 5
dataset.loc[(dataset['Age'] > 40) & (dataset['Age'] <= 66), 'Age'] = 6
dataset.loc[ dataset['Age'] > 66, 'Age'] = 6
3. Sex
Converting sex into a numeric variable
genders = {"male": 0, "female": 1}
data = [train_df, test_df]
for dataset in data:
dataset['Sex'] = dataset['Sex'].map(genders)
4. Fare
Using the “qcut()” function, that we can use to see, how we can form the categories.
data = [train_df, test_df]
for dataset in data:
dataset.loc[ dataset['Fare'] <= 7.91, 'Fare'] = 0
dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare'] = 2
dataset.loc[(dataset['Fare'] > 31) & (dataset['Fare'] <= 99), 'Fare'] = 3
dataset.loc[(dataset['Fare'] > 99) & (dataset['Fare'] <= 250), 'Fare'] = 4
dataset.loc[ dataset['Fare'] > 250, 'Fare'] = 5
dataset['Fare'] = dataset['Fare'].astype(int)
5. Embarked
This column has only 2 values, we will simply fill ‘NAs’ with the most frequent value that occurs in this column.
train_df['Embarked'].describe()
common_value = 'S'
data = [train_df, test_df]
for dataset in data:
dataset['Embarked'] = dataset['Embarked'].fillna(common_value)
New features
Fare per person
for dataset in data:
dataset['Fare_Per_Person'] = dataset['Fare']/(dataset['relatives']+1)
dataset['Fare_Per_Person'] = dataset['Fare_Per_Person'].astype(int)
##looking at the dataset
train_df.head(10)
Feature Engineering
To be added!!
Building Machine Learning Model to predict survivors
We will try different machine learning models, and compare them to pick the best one.
X_train = train_df.drop("Survived", axis=1)
Y_train = train_df["Survived"]
1. Stochastic Gradient Descent:
sgd = linear_model.SGDClassifier(max_iter=5, tol=None)
sgd.fit(X_train, Y_train)
Y_pred = sgd.predict(X_test)
sgd.score(X_train, Y_train)
acc_sgd = round(sgd.score(X_train, Y_train) * 100, 2)
2. Random Forest:
random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(X_train, Y_train)
Y_prediction = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
acc_random_forest = round(random_forest.score(X_train, Y_train) * 100, 2)
3. Logistic Regression:
logreg = LogisticRegression()
logreg.fit(X_train, Y_train)
Y_pred = logreg.predict(X_test)
acc_log = round(logreg.score(X_train, Y_train) * 100, 2)
4. K Nearest Neighbor:
KNN knn = KNeighborsClassifier(n_neighbors = 3) knn.fit(X_train, Y_train) Y_pred = knn.predict(X_test) acc_knn = round(knn.score(X_train, Y_train) * 100, 2)
5. Gaussian Naive Bayes:
gaussian = GaussianNB() gaussian.fit(X_train, Y_train) Y_pred = gaussian.predict(X_test) acc_gaussian = round(gaussian.score(X_train, Y_train) * 100, 2)
6. Perceptron:
perceptron = Perceptron(max_iter=5)
perceptron.fit(X_train, Y_train)
Y_pred = perceptron.predict(X_test)
acc_perceptron = round(perceptron.score(X_train, Y_train) * 100, 2)
7. Linear Support Vector Machine:
linear_svc = LinearSVC()
linear_svc.fit(X_train, Y_train)
Y_pred = linear_svc.predict(X_test)
acc_linear_svc = round(linear_svc.score(X_train, Y_train) * 100, 2)
8. Decision Tree
decision_tree = DecisionTreeClassifier() decision_tree.fit(X_train, Y_train) Y_pred = decision_tree.predict(X_test) acc_decision_tree = round(decision_tree.score(X_train, Y_train) * 100, 2)
Deciding the Best model
results = pd.DataFrame({
'Model': ['Support Vector Machines', 'KNN', 'Logistic Regression',
'Random Forest', 'Naive Bayes', 'Perceptron',
'Stochastic Gradient Decent',
'Decision Tree'],
'Score': [acc_linear_svc, acc_knn, acc_log,
acc_random_forest, acc_gaussian, acc_perceptron,
acc_sgd, acc_decision_tree]})
result_df = results.sort_values(by='Score', ascending=False)
result_df = result_df.set_index('Score')
result_df.head(9)
K-Fold Cross Validation:
We will measure the performance of top 3 models using K-Fold Cross Validation WHAT IS K-FOLD CROSS VALIDATION?
K-Fold Cross Validation randomly splits the training data into K subsets called folds. Let’s image we would split our data into 10 folds (when, K = 10). Our models would be trained and evaluated 10 times, using a different fold for evaluation every time, while it would be trained on the remaining 9 folds.
from sklearn.model_selection import cross_val_score
rf = RandomForestClassifier(n_estimators=100)
scores = cross_val_score(rf, X_train, Y_train, cv=10, scoring = "accuracy")
print("Scores:", scores)
print("Mean:", scores.mean())
print("Standard Deviation:", scores.std())
This gives an array of values that depict the accucary of our model on different folds. Our model has a average accuracy of 83% with a standard deviation of 3 %. The standard deviation shows us, how precise the estimates are.
What is OOB(Out of Bucket) score
print("oob score:", round(random_forest.oob_score_, 4)*100, "%")
Hyperparameter Tuning
Getting the best parameters
This will give us the best parameters for the model that we can use to increase our model performance
param_grid = { "criterion" : ["gini", "entropy"], "min_samples_leaf" : [1, 2, 5, 7, 10, 25, 50, 70], "min_samples_split" : [2, 4, 10, 12, 16, 18, 25, 35], "n_estimators": [100, 400, 700, 1000]}
from sklearn.model_selection import GridSearchCV, cross_val_score
rf = RandomForestClassifier(n_estimators=100, max_features='auto', oob_score=True, random_state=1, n_jobs=-1)
clf = GridSearchCV(estimator=rf, param_grid=param_grid, n_jobs=-1)
clf.fit(X_train, Y_train)
clf.bestparams
Testing the parameters
# Random Forest
random_forest = RandomForestClassifier(criterion = "gini",
min_samples_leaf = 1,
min_samples_split = 10,
n_estimators=100,
max_features='auto',
oob_score=True,
random_state=1,
n_jobs=-1)
random_forest.fit(X_train, Y_train)
Y_prediction = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
print("oob score:", round(random_forest.oob_score_, 4)*100, "%")
oob score: 87.35%
Calculating TPR and FPR
Confusion Matrix
from sklearn.model_selection import cross_val_predict
from sklearn.metrics import confusion_matrix
predictions = cross_val_predict(random_forest, X_train, Y_train, cv=3)
confusion_matrix(Y_train, predictions)
Precision and Recall:
from sklearn.metrics import precision_score, recall_score
print("Precision:", precision_score(Y_train, predictions))
print("Recall:",recall_score(Y_train, predictions))
F-Score
You can combine precision and recall into one score, which is called the F-score. The F-score is computed with the harmonic mean of precision and recall. Note that it assigns much more weight to low values. As a result of that, the classifier will only get a high F-score, if both recall and precision are high.
from sklearn.metrics import f1_score
f1_score(Y_train, predictions)
F-Score : 79%
However, F-Score is just a measure, it favors lower values, you will get a high F-score if you have similar Precision and Recall. In real life, you have have to choose whether you want a good precision or a higher recall. This is where you consider the Precision Recall trade-off.
###Precision Recall Curve For each person the Random Forest algorithm has to classify, it computes a probability based on a function and it classifies the person as survived (when the score is bigger the than threshold) or as not survived (when the score is smaller than the threshold). This is where the threshold’s importance comes into the picture.
from sklearn.metrics import precision_recall_curve
# getting the probabilities of our predictions
y_scores = random_forest.predict_proba(X_train)
y_scores = y_scores[:,1]
precision, recall, threshold = precision_recall_curve(Y_train, y_scores)
def plot_precision_and_recall(precision, recall, threshold):
plt.plot(threshold, precision[:-1], "r-", label="precision", linewidth=5)
plt.plot(threshold, recall[:-1], "b", label="recall", linewidth=5)
plt.xlabel("threshold", fontsize=19)
plt.legend(loc="upper right", fontsize=19)
plt.ylim([0, 1])
plt.figure(figsize=(14, 7))
plot_precision_and_recall(precision, recall, threshold)
plt.show()
Another way to plot them is
def plot_precision_vs_recall(precision, recall):
plt.plot(recall, precision, "g--", linewidth=2.5)
plt.ylabel("recall", fontsize=19)
plt.xlabel("precision", fontsize=19)
plt.axis([0, 1.5, 0, 1.5])
plt.figure(figsize=(14, 7))
plot_precision_vs_recall(precision, recall)
plt.show()
ROC Curve
This Curve plots the TPR (a.k.a. recall) and FPR (ratio of incorrectly classified negative instances) instead of precision
from sklearn.metrics import roc_curve
# compute true positive rate and false positive rate
false_positive_rate, true_positive_rate, thresholds = roc_curve(Y_train, y_scores)
# plotting them against each other
def plot_roc_curve(false_positive_rate, true_positive_rate, label=None):
plt.plot(false_positive_rate, true_positive_rate, linewidth=2, label=label)
plt.plot([0, 1], [0, 1], 'r', linewidth=4)
plt.axis([0, 1, 0, 1])
plt.xlabel('False Positive Rate (FPR)', fontsize=16)
plt.ylabel('True Positive Rate (TPR)', fontsize=16)
plt.figure(figsize=(14, 7))
plot_roc_curve(false_positive_rate, true_positive_rate)
plt.show()
ROC AUC Score
from sklearn.metrics import roc_auc_score
r_a_score = roc_auc_score(Y_train, y_scores)
print("ROC-AUC-Score:", r_a_score)
And there you have it, a decent enough first model that can be a stepping stone to your kaggle performance.
