Baseline for DCRCL

aicrowd-bot · March 27, 2020, 11:22am

Notebook

Baseline for the challenge DCRCL¶

Author - Pulkit Gera¶

In [ ]:

!pip install numpy
!pip install pandas
!pip install sklearn

Import necessary packages¶

In [20]:

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split 
from sklearn.linear_model import LogisticRegression
from sklearn import metrics

Download data¶

The first step is to download out train test data. We will be training a classifier on the train data and make predictions on test data. We submit our predictions

In [ ]:

!wget https://s3.eu-central-1.wasabisys.com/aicrowd-public-datasets/aicrowd_educational_dcrcl/data/public/test.csv
!wget https://s3.eu-central-1.wasabisys.com/aicrowd-public-datasets/aicrowd_educational_dcrcl/data/public/train.csv

Load Data¶

We use pandas library to load our data. Pandas loads them into dataframes which helps us analyze our data easily. Learn more about it here

In [2]:

train_data = pd.read_csv('train.csv')

Analyse Data¶

In [3]:

train_data.head()

Out[3]:

	LIMIT_BAL	SEX	EDUCATION	MARRIAGE	AGE	PAY_0	PAY_2	PAY_3	PAY_4	PAY_5	...	BILL_AMT4	BILL_AMT5	BILL_AMT6	PAY_AMT1	PAY_AMT2	PAY_AMT3	PAY_AMT4	PAY_AMT5	PAY_AMT6	default payment next month
0	30000	2	2	1	38	0	0	0	0	0	...	22810	25772	26360	1650	1700	1400	3355	1146	0	0
1	170000	1	4	1	28	0	0	0	-1	-1	...	11760	0	4902	14000	5695	11760	0	4902	6000	0
2	340000	1	1	2	38	0	0	0	-1	-1	...	1680	1920	9151	5000	7785	1699	1920	9151	187000	0
3	140000	2	2	2	29	0	0	0	2	0	...	65861	64848	64936	3000	8600	6	2500	2500	2500	0
4	130000	2	2	1	42	2	2	2	0	0	...	126792	103497	96991	6400	0	4535	3900	4300	3700	1

5 rows × 24 columns

Here we use the describe function to get an understanding of the data. It shows us the distribution for all the columns. You can use more functions like info() to get useful info.

In [4]:

train_data.describe()
#train_data.info()

Out[4]:

	LIMIT_BAL	SEX	EDUCATION	MARRIAGE	AGE	PAY_0	PAY_2	PAY_3	PAY_4	PAY_5	...	BILL_AMT4	BILL_AMT5	BILL_AMT6	PAY_AMT1	PAY_AMT2	PAY_AMT3	PAY_AMT4	PAY_AMT5	PAY_AMT6	default payment next month
count	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000	...	25500.000000	25500.000000	25500.000000	25500.000000	2.550000e+04	25500.000000	25500.000000	25500.000000	25500.000000	25500.000000
mean	167436.458039	1.604667	1.852824	1.551961	35.503333	-0.016275	-0.131882	-0.166706	-0.218667	-0.264157	...	43139.224941	40252.920588	38846.415529	5690.801373	5.986709e+03	5246.605294	4829.790078	4810.296706	5187.016549	0.220902
std	129837.118639	0.488932	0.791803	0.522754	9.235048	1.126813	1.196710	1.192883	1.168375	1.132166	...	64214.508636	60789.101393	59397.443604	17070.733348	2.402498e+04	18117.236738	16021.336645	15505.873498	17568.450557	0.414863
min	10000.000000	1.000000	0.000000	0.000000	21.000000	-2.000000	-2.000000	-2.000000	-2.000000	-2.000000	...	-170000.000000	-81334.000000	-209051.000000	0.000000	0.000000e+00	0.000000	0.000000	0.000000	0.000000	0.000000
25%	50000.000000	1.000000	1.000000	1.000000	28.000000	-1.000000	-1.000000	-1.000000	-1.000000	-1.000000	...	2360.000000	1779.250000	1280.000000	1000.000000	8.635000e+02	390.000000	292.750000	256.750000	113.750000	0.000000
50%	140000.000000	2.000000	2.000000	2.000000	34.000000	0.000000	0.000000	0.000000	0.000000	0.000000	...	19033.000000	18085.000000	17129.000000	2100.000000	2.010000e+03	1800.000000	1500.000000	1500.000000	1500.000000	0.000000
75%	240000.000000	2.000000	2.000000	2.000000	42.000000	0.000000	0.000000	0.000000	0.000000	0.000000	...	54084.750000	50080.750000	49110.500000	5006.000000	5.000000e+03	4507.000000	4001.250000	4024.000000	4000.000000	0.000000
max	1000000.000000	2.000000	6.000000	3.000000	79.000000	8.000000	8.000000	8.000000	8.000000	8.000000	...	891586.000000	927171.000000	961664.000000	873552.000000	1.684259e+06	896040.000000	621000.000000	426529.000000	527143.000000	1.000000

8 rows × 24 columns

Split Data into Train and Validation¶

Now we want to see how well our classifier is performing, but we dont have the test data labels with us to check. What do we do ? So we split our dataset into train and validation. The idea is that we test our classifier on validation set in order to get an idea of how well our classifier works. This way we can also ensure that we dont overfit on the train dataset. There are many ways to do validation like k-fold,leave one out, etc

In [5]:

X = train_data.drop('default payment next month',1)
y = train_data['default payment next month']
# Validation testing
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)

Here we have selected the size of the validation data to be 20% of the total data. You can change it and see what effect it has on the accuracies. To learn more about the train_test_split function click here.

Define the Classifier and Train¶

Now we come to the juicy part. We have fixed our data and now we train a classifier. The classifier will learn the function by looking at the inputs and corresponding outputs. There are a ton of classifiers to choose from some being Logistic Regression, SVM, Random Forests, Decision Trees, etc.
Tip: A good model doesnt depend solely on the classifier but on the features(columns) you choose. So make sure to play with your data and keep only whats important.

In [6]:

classifier = LogisticRegression()
classifier.fit(X_train,y_train)

# from sklearn.svm import SVC
# clf = SVC(gamma='auto')
# clf.fit(X_train, y_train)

# from sklearn import tree
# clf = tree.DecisionTreeClassifier()
# clf = clf.fit(X_train, y_train)

/home/gera/anaconda3/lib/python3.6/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)

Out[6]:

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
                   intercept_scaling=1, l1_ratio=None, max_iter=100,
                   multi_class='warn', n_jobs=None, penalty='l2',
                   random_state=None, solver='warn', tol=0.0001, verbose=0,
                   warm_start=False)

We have used Logistic Regression as a classifier here and set few of the parameteres. But one can set more parameters and increase the performance. To see the list of parameters visit here.
Also given are SVM and Decision Tree examples. Check out SVM's parameters here and Decision Tree's here

got a warning! Dont worry, its just beacuse the number of iteration is very less(defined in the classifier in the above cell).Increase the number of iterations and see if the warning vanishes.Do remember increasing iterations also increases the running time.( Hint: max_iter=500)

Predict on Validation¶

Now we predict our trained classifier on the validation set and evaluate our model

In [7]:

y_pred = classifier.predict(X_val)

In [8]:

df = pd.DataFrame({'Actual': y_val, 'Predicted': y_pred})
df1 = df.head(25)
df1

Out[8]:

	Actual	Predicted
6913	0	0
11124	0	0
25100	1	0
2764	0	0
23216	0	0
17269	0	0
3073	0	0
8184	0	0
2595	0	0
5483	0	0
6508	0	0
11776	0	0
5306	0	0
18846	0	0
19854	0	0
2463	0	0
5304	0	0
23739	0	0
20427	0	0
20263	0	0
9578	0	0
14164	0	0
5107	0	0
5160	0	0
8450	0	0

Evaluate the Performance¶

We use the same metrics as that will be used for the test set.
F1 score and ROC AUC are the metrics for this challenge

In [9]:

print('F1 score Score:', metrics.f1_score(y_val, y_pred))  
print('ROC AUC Score:', metrics.roc_auc_score(y_val, y_pred))

F1 score Error: 0.0
ROC AUC Error: 0.49975062344139654

Load Test Set¶

Load the test data now

In [10]:

test_data = pd.read_csv('test.csv')

Predict Test Set¶

Time for the moment of truth! Predict on test set and time to make the submission.

In [11]:

y_test = classifier.predict(test_data)

In [12]:

df = pd.DataFrame(y_test,columns=['default payment next month'])
df.to_csv('submission.csv',index=False)

To download the generated csv in collab run the below command¶

In [ ]:

from google.colab import files
files.download('submission.csv')

To participate in the challenge click here