Baseline Model Titanic

Shows the usage of aiking library on a kaggle dataset

Import public packages

import fastcore
import pandas as pd
import pathlib
from fastcore.all import *
from fastcore.imports import *
import os
import sys
import sklearn
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_score, cross_val_predict, KFold, train_test_split, cross_validate
from sklearn.metrics import ConfusionMatrixDisplay, accuracy_score, confusion_matrix
from IPython.display import display
from sklearn.pipeline import make_pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder

Import private packages

is_kaggle = 'kaggle_secrets' in sys.modules
if is_kaggle:
    from kaggle_secrets import UserSecretsClient
    user_secrets = UserSecretsClient()
    os.environ['KAGGLE_USERNAME'] = user_secrets.get_secret("kaggle_username")
    if not os.environ['KAGGLE_USERNAME']: raise Exception("Please insert your Kaggle username and key into Kaggle secrets")
    os.environ['KAGGLE_KEY'] = user_secrets.get_secret("kaggle_key")
    github_pat = user_secrets.get_secret("GITHUB_PAT")
    !pip install -Uqq git+https://{github_pat}@github.com/Rahuketu86/aiking
else:
    from aiking.data.external import *
    path = untar_data("kaggle_competitions::titanic"); 
    print(path.ls())
[Path('/Users/rahul1.saraf/rahuketu/programming/AIKING_HOME/data/titanic/test.csv'), Path('/Users/rahul1.saraf/rahuketu/programming/AIKING_HOME/data/titanic/train.csv'), Path('/Users/rahul1.saraf/rahuketu/programming/AIKING_HOME/data/titanic/gender_submission.csv')]
from aiking.ml.structured import *

Read the Dataset

data_dir = pathlib.Path(os.getenv('DATA_DIR', "/kaggle/input")); 
path = data_dir/"titanic"
path.ls()
(#3) [Path('/Users/rahul1.saraf/rahuketu/programming/AIKING_HOME/data/titanic/test.csv'),Path('/Users/rahul1.saraf/rahuketu/programming/AIKING_HOME/data/titanic/train.csv'),Path('/Users/rahul1.saraf/rahuketu/programming/AIKING_HOME/data/titanic/gender_submission.csv')]
df_train = pd.read_csv(path/"train.csv"); df_train.head()
df_test = pd.read_csv(path/"test.csv"); df_test.head()
PassengerId Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked
0 892 3 Kelly, Mr. James male 34.5 0 0 330911 7.8292 NaN Q
1 893 3 Wilkes, Mrs. James (Ellen Needs) female 47.0 1 0 363272 7.0000 NaN S
2 894 2 Myles, Mr. Thomas Francis male 62.0 0 0 240276 9.6875 NaN Q
3 895 3 Wirz, Mr. Albert male 27.0 0 0 315154 8.6625 NaN S
4 896 3 Hirvonen, Mrs. Alexander (Helga E Lindqvist) female 22.0 1 1 3101298 12.2875 NaN S 
df_train.describe(include='all').T
count unique top freq mean std min 25% 50% 75% max
PassengerId 891.0 NaN NaN NaN 446.0 257.353842 1.0 223.5 446.0 668.5 891.0
Survived 891.0 NaN NaN NaN 0.383838 0.486592 0.0 0.0 0.0 1.0 1.0
Pclass 891.0 NaN NaN NaN 2.308642 0.836071 1.0 2.0 3.0 3.0 3.0
Name 891 891 Braund, Mr. Owen Harris 1 NaN NaN NaN NaN NaN NaN NaN
Sex 891 2 male 577 NaN NaN NaN NaN NaN NaN NaN
Age 714.0 NaN NaN NaN 29.699118 14.526497 0.42 20.125 28.0 38.0 80.0
SibSp 891.0 NaN NaN NaN 0.523008 1.102743 0.0 0.0 0.0 1.0 8.0
Parch 891.0 NaN NaN NaN 0.381594 0.806057 0.0 0.0 0.0 0.0 6.0
Ticket 891 681 347082 7 NaN NaN NaN NaN NaN NaN NaN
Fare 891.0 NaN NaN NaN 32.204208 49.693429 0.0 7.9104 14.4542 31.0 512.3292
Cabin 204 147 B96 B98 4 NaN NaN NaN NaN NaN NaN NaN
Embarked 889 3 S 644 NaN NaN NaN NaN NaN NaN NaN

Modelling

Define Pipeline

def get_model_pipeline(max_n_cat=0, 
                       cat_dict=None, 
                       scale_dict={'class': StandardScaler},
                       cat_num_dict={'class':NumericalEncoder,'categories':None},
                       cat_dummy_dict={'class':OneHotEncoder,'handle_unknown':'ignore'},
                       imputer_dict={'class':SimpleImputer, 'strategy':'median'},
                      ):
    layer_spec_default = (get_default_feature_def, 
                      {
                          'skip_flds':None, 
                          'ignored_flds':None, 
                          'max_n_cat':max_n_cat, 
                          'na_exclude_cols':[],
                          'scale_var_num':True,
                          'scale_var_cat':False,
                          'scale_dict':scale_dict,
                          'cat_num_dict':cat_num_dict,
                          'cat_dummy_dict':cat_dummy_dict,
                          'imputer_dict':imputer_dict,
                          'include_time_cols':True,
                          'keep_dt_cols':False,
                          'cat_dict':cat_dict
                      }
                     )

    layer_specs = [layer_spec_default]
    proc = Proc(layer_specs=layer_specs); #proc.fit_transform(X)
    model = RandomForestClassifier(n_jobs=-1)
    pipeline = make_pipeline(proc, model); pipeline
    return pipeline
pipeline = get_model_pipeline(cat_dict=None); pipeline
Pipeline(steps=[('proc', <aiking.ml.structured.Proc object at 0x155257070>),
                ('randomforestclassifier', RandomForestClassifier(n_jobs=-1))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Train on Partial Data

max_n_cat = 5

def get_xy(df, col='Survived'): return df.drop([col], axis=1), df[col]
    
X, y = get_xy(df_train)

pipeline = get_model_pipeline(max_n_cat,cat_dict=None)
pipeline.fit(X, y)
Pipeline(steps=[('proc', <aiking.ml.structured.Proc object at 0x155257c40>),
                ('randomforestclassifier', RandomForestClassifier(n_jobs=-1))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
get_scorer_dict(scorer_names=['accuracy', 'precision', 'recall', 'roc_auc'])
{'accuracy': make_scorer(accuracy_score),
 'precision': make_scorer(precision_score, average=binary),
 'recall': make_scorer(recall_score, average=binary),
 'roc_auc': make_scorer(roc_auc_score, needs_threshold=True)}

This gives an indication of estimate of msle around .26 to .30[Really 0.304 from validation estimate]

Cross validation estimate

pipeline = get_model_pipeline(max_n_cat,cat_dict=None)
# scores = cross_val_score(pipeline, X, y, scoring='accuracy'); scores
scores_df = pd.DataFrame(cross_validate(pipeline, X, y, scoring=['accuracy', 'precision', 'recall', 'roc_auc'])); scores_df
fit_time score_time test_accuracy test_precision test_recall test_roc_auc
0 1.532780 0.041193 0.776536 0.737705 0.652174 0.830303
1 0.068360 0.036002 0.747191 0.641975 0.764706 0.808690
2 0.063332 0.034494 0.792135 0.674157 0.882353 0.902473
3 0.063486 0.035383 0.814607 0.786885 0.705882 0.867112
4 0.060760 0.037809 0.808989 0.716049 0.840580 0.892833 
scores_df.plot()

# pipeline = get_model_pipeline(cat_dict); pipeline
y_pred = cross_val_predict(pipeline, X, y)
# cm = confusion_matrix(y, y_pred)
# disp = ConfusionMatrixDisplay(confusion_matrix=cm)
# disp.plot()
ConfusionMatrixDisplay.from_predictions(y, y_pred)

scores = scores_df['test_accuracy']
print(f"Expected Scores {scores.mean() - 3*scores.std():.2%} to {scores.mean() + 3*scores.std():.2%} with mean as {scores.mean():.2%}")
Expected Scores 70.63% to 86.95% with mean as 78.79%

Predictions

Retrain pipeline on complete dataset

pipeline = get_model_pipeline(max_n_cat,cat_dict=None)
pipeline.fit(X, y)
y_pred = pipeline.predict(X)
cm = confusion_matrix(y, y_pred)
disp = ConfusionMatrixDisplay(confusion_matrix=cm)
display(disp.plot(), accuracy_score(y, y_pred))
<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay>
1.0

Calculation for test set and submission

df_sample_submission = pd.read_csv(path/"gender_submission.csv"); df_sample_submission.head()
PassengerId Survived
0 892 0
1 893 1
2 894 0
3 895 0
4 896 1 
os.getcwd()
'/Users/rahul1.saraf/rahuketu/programming/portfolio/curations/competitions/titanic'
predictions = pd.DataFrame(pipeline.predict(df_test), columns=[y.squeeze().name]); predictions
df_submission = pd.concat([df_test['PassengerId'], predictions], axis=1); df_submission
df_submission.to_csv('submission.csv', index=False)
if not is_kaggle:
    import kaggle
    kaggle.api.competition_submit_cli("submission.csv", "Submission from local machine", competition="titanic")
    # from aiking.integrations.kaggle import push2kaggle
    # push2kaggle("00_index.ipynb")
Warning: Looks like you're using an outdated API Version, please consider updating (server 1.6.12 / client 1.5.16)
100%|██████████████████████████████████████| 2.77k/2.77k [00:01<00:00, 1.77kB/s]