{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Introduction: Home Credit Default Risk Competition\n\nThis notebook is intended for those who are new to machine learning competitions or wnat a gentle introduction to the problem. I purposely avoid jumping into complicated models or joining together lots of data in ordef to show the basics of how to get started in machine learning! Any commnets of surggestions are much appreciated.\n\nIn this notebook, we will take an initial look at the Home Credit default risk machine learning competition currently hosted on Kaggle. The objective of this competition is to use historical loan application data to predict whether or not an applicant will be albe to repay a loan. This is a standard supervised classifiaction task:\n\n- **Superviesd**: The labels are included in the training data and the goal is to train a model to learn to predict the labels frome the features.\n\n- **Classification**: The label is a binary variable, 0 (will repay loan on time), 1 (will have difficulty repaying loan)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"# Data\n\nThe data is provided by [Hoem Credit](http://www.homecredit.net/about-us.aspx), a service dedicated to provided lines of credit (loan) to the unbanked population. Predicting whether or not a client will repay a loan or have difficulty is a critical business need, and Home Credit is hosting this competition on Kaggle to see what sort of models the machine learning community can develop to help them in this task.\n\nThere are 7 different sources of data:\n\n- **application_train/application_test**: the main training and testing data with inforamtion about each loan application at Home Credit. Every loan has its own row and is identified by feature **SK_ID_CURR**. The training application data comes with the **TARGET** indicating 0: the loan was repaid or 1: the loan was not repaid.\n\n- **bureau**: data concerning client's previous credits from other financial institutions. Each previous credit has its own row in bureau, but one loan in the application data can have multiple previous credits.\n\n- **bureau_balance**: monthly data about the previous credits in bureau. Each row is one month of a previous credit and a single previous credit can have multiple rows, one for each month of the credit length.\n\n- **previous_application**: previous applications for loans at Home Credit of clients who have loans in the application data. Each current loan in the application data can have multiple previous loans. Each previous application has one row and is identified by the feature **SK_ID_PREV**.\n\n- **POS_CASH_BALANCE**: monthly data about previous point of sale or cash loans clients have had with Home Credit. Each row is one month of a previous point of slae or cash loan, and a single previous loan can have many rows.\n\n- **credit_card_balance**: monthly data about precious credit cards clients have had with Home Credit. Each row is ont month of a credit card balance, and a single credit card can have many rows.\n\n- **installments_payment**: payment history for previous loans at Home Credit. There is one row for every made payment and one row for every missed payment.\n\nThis diagram shhow how all of the data is related:\n\n![image.png](attachment:848b9d57-71ff-4a08-8472-6f3d1d9457be.png)![image.png](attachment:177347d1-aeb8-43fa-8fbb-679a927d3f16.png)\n\nMoreover, we are provided with the definitions of all the columns (in **HomeCredit_columns_description.csv**) and an example of the expected submission file.\n\nIn this notebook, we will stick to using only the main application training and testing data. Although if we want to have any hope of seriously competing, we need to use all the data, for now we will stick to on file which shoild be more manageable. This will let us establish a baseline that we can then imporve upon. With these projects, it's best to build up an understanding of the problem a little at a time rather than diving all the way in and getting completely lost!","metadata":{},"attachments":{"848b9d57-71ff-4a08-8472-6f3d1d9457be.png":{"image/png":"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"},"177347d1-aeb8-43fa-8fbb-679a927d3f16.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# Metric: ROC AUC\n\nOnce we have a grasp of the data (reading through the [column descriptions](https://www.kaggle.com/c/home-credit-default-risk/data) helps immensely), we need to understand the metric by which our submission is judged. In this case, it is a common classification metric known as the [Receiver Operating Characterisic Area Under the Curev(ROC AUC, also sometimes called AUROC)](https://stats.stackexchange.com/questions/132777/what-does-auc-stand-for-and-what-is-it).\n\nThe ROC AUC may sound intimidating, but it is relatively straightforward once you can get your head around the two individual concepys. The [Receiver Operating Characteristic (ROC) curve](https://en.wikipedia.org/wiki/Receiver_operating_characteristic) graphs the true positive rate versus the false positive rate:\n\n![image.png](attachment:933b9a9a-e8d6-455f-babd-96f2a41b2605.png)\n\nA single line on the graph indicates the curve for a single model, and movement aalong a line indicates changing the threshold used for classifying a positive instance. The threshold starts at 0 in the upper right to and goes to 1 in the lower left. A curve that is to the left and above another curve indicates a better model. For example, the blue model is better than the red model, which is better than the black diagonal line which indicates a navie random guessing model.\n\nThe [Area Under the Curve (AUC)](https://en.wikipedia.org/wiki/Receiver_operating_characteristic) explains itself by its name! It is simply the area under the ROC curve. (This is the integral of the curve.) This metrci is between 0 and 1 with a better model scoring higher. A model that simply guesses at random will have an ROC AUC of 0.5.\n\nWhen we measure a classifier according to the ROC AUC, we do not generation 0 ir 1 predictions, but rather a probability between 0 and 1. This may be confusing because we usually like to think in terms of accuracy, but when we get into provlems with inbalanced classes (we will see this is the case), accuracy is not the best metric. For example, if I wanted to build a model that could detect terrorists with 99.9999% accuracy, I would simply make a model that predicted every single person was not a terrorist. Clearly, this would not be effective (the recall would be zero) and we use more advanced metrics such as ROC AUC or the [F1 score](https://en.wikipedia.org/wiki/F1_score) to more accurately reflect the performance of a classifier. A model with a high ROC AUC will also have a high accuracy, but the [ROC AUC is a better representation of model performance](https://datascience.stackexchange.com/questions/806/advantages-of-auc-vs-standard-accuracy).\n\nNot that we know the background of the data we are using and the metric to maximize, let's get into exploring the data. In this notebook, as mentioned previously, we will stick to the main data sources and simple models which we can build upon in future work.\n\n**Follow-up Notebooks**\n\nFor those looking to keep working on this problem, I have a series of follow-up notebooks:\n\n- Manual Feature Engineering Part One\n- Manual Feature Engineering Part Two\n- Introduction to Automated Feature Engineering\n- Advanced Automated Feature Engineering\n- Feature Selection\n- Intro to Model Tuning: Grid and Random Search\n- Automated Model Tuning\n- Model Tuning Results\n\nI'll add more notebooks as I finish them! Thanks for all the comments!","metadata":{},"attachments":{"933b9a9a-e8d6-455f-babd-96f2a41b2605.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"## Import\n\nwe are using a typical data science stack: numpy, pandas, sklearn, matplotlib.","metadata":{}},{"cell_type":"code","source":"# numpy and pandas for data manipulation\nimport numpy as np\nimport pandas as pd\n\n# sklearn preprocessing for dealing with categorical variables\nfrom sklearn.preprocessing import LabelEncoder\n\n# File system management\nimport os\n\n# Suppress warnings\nimport warnings\nwarnings.filterwarnings('ignore')\n\n# matplotlib and seaborn for plotting\nimport matplotlib.pyplot as plt\nimport seaborn as sns","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:26:52.632577Z","iopub.execute_input":"2022-07-26T04:26:52.632967Z","iopub.status.idle":"2022-07-26T04:26:53.185232Z","shell.execute_reply.started":"2022-07-26T04:26:52.632932Z","shell.execute_reply":"2022-07-26T04:26:53.184368Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Read in Data\n\nFirst, we can list all the available data files. There are a total of 9 files: 1 main file for training (with target) 1 main file for testing (without the target), 1 example submission file, and 6 other files containing additional information about each loan.","metadata":{}},{"cell_type":"code","source":"# List files available\nprint(os.listdir('../input/home-credit-default-risk'))","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:26:53.543826Z","iopub.execute_input":"2022-07-26T04:26:53.544536Z","iopub.status.idle":"2022-07-26T04:26:53.551754Z","shell.execute_reply.started":"2022-07-26T04:26:53.544490Z","shell.execute_reply":"2022-07-26T04:26:53.550681Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Training data\napp_train = pd.read_csv('../input/home-credit-default-risk/application_train.csv')\nprint('Training data shape: ', app_train.shape)\napp_train.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:26:54.134405Z","iopub.execute_input":"2022-07-26T04:26:54.135221Z","iopub.status.idle":"2022-07-26T04:27:00.302787Z","shell.execute_reply.started":"2022-07-26T04:26:54.135176Z","shell.execute_reply":"2022-07-26T04:27:00.301536Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The training data has 307511 observations (each one a separate loan) and 122 features (variables) including the TARGET (the label we want to predict)","metadata":{}},{"cell_type":"code","source":"# Testing data features\napp_test = pd.read_csv('../input/home-credit-default-risk/application_test.csv')\nprint('Testing data shape: ', app_test.shape)\napp_test.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:00.306297Z","iopub.execute_input":"2022-07-26T04:27:00.306636Z","iopub.status.idle":"2022-07-26T04:27:01.240499Z","shell.execute_reply.started":"2022-07-26T04:27:00.306605Z","shell.execute_reply":"2022-07-26T04:27:01.239486Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The test set is considerably smaller and lacks a TARGET column.","metadata":{}},{"cell_type":"markdown","source":"# Exploratory Data Analysis\n\nExploratory Data Analysis (EDA) is an open-ended process where we calculate statistics and make figures to find trends, anomalies, patterns, or relationships within the data. The goal of EDA is to learn what our data can tell us. It generally starts out with a high level overveiw, then narrows in to specific areas as we find intriguing areas of the data. The findings may be interesing in their own right, or they can be used to infrom our modeling chicesm such as by helping us decide which features to use.","metadata":{}},{"cell_type":"markdown","source":"## Examine the Distribution for the Target Column\n\nThe target is what we are asked to predict: either a 0 for loan was repaid on time, or a 1 indicating the client had payment difficulties. We can first examine the number of loans falling into each category.","metadata":{}},{"cell_type":"code","source":"app_train['TARGET'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:01.241690Z","iopub.execute_input":"2022-07-26T04:27:01.242019Z","iopub.status.idle":"2022-07-26T04:27:01.258138Z","shell.execute_reply.started":"2022-07-26T04:27:01.241990Z","shell.execute_reply":"2022-07-26T04:27:01.256880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"app_train['TARGET'].astype(int).plot.hist();","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:01.260642Z","iopub.execute_input":"2022-07-26T04:27:01.261383Z","iopub.status.idle":"2022-07-26T04:27:01.501513Z","shell.execute_reply.started":"2022-07-26T04:27:01.261332Z","shell.execute_reply":"2022-07-26T04:27:01.500399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"From this information, we see this is an [imbalanced class problem](http://www.chioka.in/class-imbalance-problem/). There are far more loans that were repaid on time than loans that were not repaid. Once we get into more sophisicated machine learning models, we can [weight the classes](http://xgboost.readthedocs.io/en/latest/parameter.html) by their representation in the data to reflect this imbalance.","metadata":{}},{"cell_type":"markdown","source":"## Examine Missin Values\n\nNext we can look at the number and percentage of missing values in each column.","metadata":{}},{"cell_type":"code","source":"# Function to calculate missing values by column # Funct\ndef missing_values_table(df):\n    # Total missing values\n    mis_val = df.isnull().sum()\n    \n    # Percentage of missing values\n    mis_val_percentage = 100 * df.isnull().sum() / len(df)\n    \n    # Make a table with te results\n    mis_val_table = pd.concat([mis_val, mis_val_percentage], axis= 1)\n    \n    # Rename the columns\n    mis_val_table_ren_columns = mis_val_table.rename(\n        columns = {0: 'Missing Values', 1: '% of Total Values'})\n    \n    # Sort the table by percentage of missing descending\n    mis_val_table_ren_columns = mis_val_table_ren_columns[\n        mis_val_table_ren_columns.iloc[:, 1] != 0].sort_values(\n    '% of Total Values', ascending= False).round(1)\n    \n    # Print some summary information\n    print('Your selected dataframe has ' + str(df.shape[1]) + ' columns.\\n'\n         'There are ' + str(mis_val_table_ren_columns.shape[0]) + \n         ' columns that have missing values.')\n    \n    # Return the dataframe with missing information\n    return mis_val_table_ren_columns","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:01.502644Z","iopub.execute_input":"2022-07-26T04:27:01.502999Z","iopub.status.idle":"2022-07-26T04:27:01.512074Z","shell.execute_reply.started":"2022-07-26T04:27:01.502968Z","shell.execute_reply":"2022-07-26T04:27:01.510788Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Missing values statistics\nmissing_values = missing_values_table(app_train)\nmissing_values.head(20)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:01.514092Z","iopub.execute_input":"2022-07-26T04:27:01.514541Z","iopub.status.idle":"2022-07-26T04:27:02.595324Z","shell.execute_reply.started":"2022-07-26T04:27:01.514497Z","shell.execute_reply":"2022-07-26T04:27:02.594076Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"When it comes time to build our machine learning models, we will have to fill in these missing values (known as imputation). In later work, we will use models such as XGBoost that can [handle missing values with no need for imputation](https://stats.stackexchange.com/questions/235489/xgboost-can-handle-missing-data-in-the-forecasting-phase). Another option would be to drop columns with a high percentage of missing values, although it is impossible to know ahead of time if these columns will be helpful to our model. Therefore, we will keep all of the columns for now.","metadata":{}},{"cell_type":"markdown","source":"## Column Types\n\nLet's look at the number of columns of each data type. int64 and float64 are numeric variables ([which can be either discrete or continuous](https://stats.stackexchange.com/questions/206/what-is-the-difference-between-discrete-data-and-continuous-data)). object columns contain strings and are [categorical features](http://support.minitab.com/en-us/minitab-express/1/help-and-how-to/modeling-statistics/regression/supporting-topics/basics/what-are-categorical-discrete-and-continuous-variables/).","metadata":{}},{"cell_type":"code","source":"# Number of each type of column\napp_train.dtypes.value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:02.597034Z","iopub.execute_input":"2022-07-26T04:27:02.597567Z","iopub.status.idle":"2022-07-26T04:27:02.608431Z","shell.execute_reply.started":"2022-07-26T04:27:02.597520Z","shell.execute_reply":"2022-07-26T04:27:02.607144Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Let's now look at the number of unique entries in each of the object (categorical) columns.","metadata":{}},{"cell_type":"code","source":"# Number of unique classes in each object column\napp_train.select_dtypes('object').apply(pd.Series.nunique, axis= 0)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:02.609555Z","iopub.execute_input":"2022-07-26T04:27:02.609892Z","iopub.status.idle":"2022-07-26T04:27:03.106850Z","shell.execute_reply.started":"2022-07-26T04:27:02.609856Z","shell.execute_reply":"2022-07-26T04:27:03.106075Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Most of the categorical variables have a relatively small number of unique entries. We will need to find a way to deal with these categorical variables!","metadata":{}},{"cell_type":"markdown","source":"## Encoding Categorical Variables\n\nBefore we go any futher, we need to deal with pesky categorical variables. A machine leanring model unfortunately cannot deal with categorical variables (except for some models such as [LightGBM](http://lightgbm.readthedocs.io/en/latest/Features.html)). Therefore, we have to find a way to encode (represent) these variables as numbers before handing them off to the model.\n\nThere are two main ways to carry out this process:\n\n- Label encoding: assign each unique category in a categorical variable with an integer. No new columns are created. An example is shown below\n\n![image.png](attachment:13b01a75-33f9-4c09-a4f1-93dc8cf9ed46.png)\n\n- One-hot encoding: create a new column for each unique category in a categorical variable. Each observation recieves a 1 in the column for its corresponding category and a 0 in all other new columns.\n\n![image.png](attachment:173ee64b-4e39-413b-a478-15a0bede822b.png)\n\nThe problem with label encoding is that it gives the categories an arbitrary ordering. The value assigned to each of the categories is random and does not reflect any ingerent aspect of the category. In the example above, programmer recieves a 4 and data scientist a 1, but if we did the same process again, the labels could be reversed or completely different. The actual assignment of the integers is arbitrary. Therefore, when we perform label encoding, the model might use the relative value of the feature (for example programmer = 4 and data scientist = 1) to assign weights which is not what we want. If we only have two unique values for a categorical variable (such as Male/Female), then label encoding is fine, but more than 2 unique categories, one-hot encoding is the safe option.\n\nThere is some debate about the relative merits of these approaches, and some models can deal with label encoded categorical variables with no issues. [Here is a good Stack Overflow discusion](https://datascience.stackexchange.com/questions/9443/when-to-use-one-hot-encoding-vs-labelencoder-vs-dictvectorizor). I think (and this is just a personal option) for categorical variables with many classes, one-hot encoding is the safest approach beacuse it does not impose arbitrary values to categories. The only downside to one-hot encoding is that the number of features (dimensions of the data) can explode with categorical variables with many categories. To deal with this, we can perform one-hot encoding followed by PCA or other dimensionality reduction methods to reduce the number of dimnesions (while shill trying to preserve information).\n\nIn this notebook, we will use Label Encoding for any categorical variables with only 2 categories and One-Hot Encoding for any categorical variables with more than 2 categories. This process may need to change as we get further into the project, but for now, we will see where this gets us. (We will also not use any dimensionality reduction in this notebook but will explore in future iterations).","metadata":{},"attachments":{"13b01a75-33f9-4c09-a4f1-93dc8cf9ed46.png":{"image/png":"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"},"173ee64b-4e39-413b-a478-15a0bede822b.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"### Label Encoding and One-Hot Encoding\n\nLet's implement the policy described above: for any categorical variable( dtype == object ) with 2 unique categories, we will use label encoding, and for any categorical variable with more than 2 unique categories, we will use one-hot encoding.\n\nFor label encoding, we use the Scikit-Learn LabelEncoder and for one-hot encoding, the pandas get_dummies(df) function.","metadata":{}},{"cell_type":"code","source":"# Create a label encoder object\nle = LabelEncoder()\nle_count = 0\n\n# Iterate through the columns\nfor col in app_train:\n    if app_train[col].dtype == 'object':\n        # If 2 or fewer unique categories\n        if len(list(app_train[col].unique())) <= 2:\n            # Train on the training data\n            le.fit(app_train[col])\n            # Transform both training and testing data\n            app_train[col] = le.transform(app_train[col])\n            app_test[col] = le.transform(app_test[col])\n            \n            # Keep track of how many columns were label encoded\n            le_count += 1\n            \nprint('%d columns were label encoded.' % le_count)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:03.107867Z","iopub.execute_input":"2022-07-26T04:27:03.108443Z","iopub.status.idle":"2022-07-26T04:27:04.149666Z","shell.execute_reply.started":"2022-07-26T04:27:03.108410Z","shell.execute_reply":"2022-07-26T04:27:04.148377Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# one-hot encoding of categorical variables\napp_train = pd.get_dummies(app_train)\napp_test = pd.get_dummies(app_test)\n\nprint('Training Features shape: ', app_train.shape)\nprint('Testing Features shape: ', app_test.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:04.153344Z","iopub.execute_input":"2022-07-26T04:27:04.153729Z","iopub.status.idle":"2022-07-26T04:27:05.650652Z","shell.execute_reply.started":"2022-07-26T04:27:04.153673Z","shell.execute_reply":"2022-07-26T04:27:05.649413Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Aligning Training and Testing Data\n\nThere need to be the same features (columns) in both the training and testing data. One-hot encoding has created more columns in the training data because there were some categorical variables with categoris not represented in the testing data. To remove the columns in the training data that are not in the testing data, we need to align the dataframes. First we extract the target column from the training data (because this is not in the testing data but we need to keep this information). When we do the align, we must make sure to set axis =1 to align the dataframes based on the columns and not no the rows!","metadata":{}},{"cell_type":"code","source":"train_labels = app_train['TARGET']\n\n# Align the training and testing data, keep only columns present in both dataframes\napp_train, app_test = app_train.align(app_test, join = 'inner', axis =1)\n\n# Add the target back in\napp_train['TARGET'] = train_labels\n\nprint('Training Features shape: ', app_train.shape)\nprint('Testing Features shape: ', app_test.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:05.652313Z","iopub.execute_input":"2022-07-26T04:27:05.652785Z","iopub.status.idle":"2022-07-26T04:27:06.239769Z","shell.execute_reply.started":"2022-07-26T04:27:05.652737Z","shell.execute_reply":"2022-07-26T04:27:06.238436Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The training and testing datasets now have the same features which is required for machine learning. The number of features has grown significantly due to one-hot encoding. At some point we probablt will want to try [dimensionality reduction (removing features that are not relevant](https://en.wikipedia.org/wiki/Dimensionality_reduction)) to reduce the size of the datasets.","metadata":{}},{"cell_type":"markdown","source":"## Back to Exploratory Data Analysis","metadata":{}},{"cell_type":"markdown","source":"### Anomalies\n\nOne problem we always want to be on the lookout for when doing EDA is anomalies within the data. These may be due to mis-typed numbers, errors in measuring equipment, or they could bo valid but extreme measuremnets. One way to support anomalies quantitaively is by looking at the statistics of a column using the describe method. The numbers in the DAYS_BIRTH column are negative because they are recorded relative to the current loan application. To see these stats in years, we can multiple by -1 and divide by the number of days in a year:","metadata":{}},{"cell_type":"code","source":"(app_train['DAYS_BIRTH'] / -365).describe()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:06.241588Z","iopub.execute_input":"2022-07-26T04:27:06.242152Z","iopub.status.idle":"2022-07-26T04:27:06.272414Z","shell.execute_reply.started":"2022-07-26T04:27:06.242107Z","shell.execute_reply":"2022-07-26T04:27:06.271209Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Those ages look reasonable. There are no outliers for the age on either the high or low end. How about the days of employment?","metadata":{}},{"cell_type":"code","source":"app_train['DAYS_EMPLOYED'].describe()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:06.273633Z","iopub.execute_input":"2022-07-26T04:27:06.273950Z","iopub.status.idle":"2022-07-26T04:27:06.294058Z","shell.execute_reply.started":"2022-07-26T04:27:06.273922Z","shell.execute_reply":"2022-07-26T04:27:06.293069Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"That doesn't look right! The maximum value (besides being positive) is about 1000 years!","metadata":{}},{"cell_type":"code","source":"app_train['DAYS_EMPLOYED'].plot.hist(title = 'Days Employment Histogram');\nplt.xlabel('Days Employment');","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:06.295430Z","iopub.execute_input":"2022-07-26T04:27:06.295784Z","iopub.status.idle":"2022-07-26T04:27:06.555397Z","shell.execute_reply.started":"2022-07-26T04:27:06.295749Z","shell.execute_reply":"2022-07-26T04:27:06.554017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Just out of curiousity, let's subset the anomalous clients and see if they tend to have higher or low rates of default than the rest of the clients.","metadata":{}},{"cell_type":"code","source":"anom = app_train[app_train['DAYS_EMPLOYED'] == 365243]\nnon_anom = app_train[app_train['DAYS_EMPLOYED'] != 365243]\nprint('The non_anomalies default on %0.2f%% of loans' % (100 * non_anom['TARGET'].mean()))\nprint('The anomalies default on %0.2f%% of loans' % (100 * anom['TARGET'].mean()))\nprint('There are %d anomalous days of employment' % len(anom))","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:06.557348Z","iopub.execute_input":"2022-07-26T04:27:06.558151Z","iopub.status.idle":"2022-07-26T04:27:07.190570Z","shell.execute_reply.started":"2022-07-26T04:27:06.558105Z","shell.execute_reply":"2022-07-26T04:27:07.189473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Well that is extremely interesting! It tunrs out that the anomalies have a rate of default.\n\nHandling the anomalies depends on the exact situation, with no set rules. One of the safest approaches is just to set the anomalies to a missing value and then have them filled in (using Inputation) before machine learning. In this case, since all the anomalies have the exact same value, we want to fill them in with the same value in case all of these loans share something in common. The anomalous values seem to have some importance, so we want to tell the machine leanring model if we did in fact fill in these values. As a solution, we will fill in the anomalous values with not a number (np.nan) and then create a new boolean indicating whether or not the values was anomalous.","metadata":{}},{"cell_type":"code","source":"# Create an anomalous flag column\napp_train['DAYS_EMPLOYED_ANOM'] = app_train['DAYS_EMPLOYED'] == 365243\n\n# Replace the anomalous values with nan\napp_train['DAYS_EMPLOYED'].replace({365243: np.nan}, inplace= True)\n\napp_train['DAYS_EMPLOYED'].plot.hist(title = 'Days Employment Histogram')\nplt.xlabel('Days Employment')","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:07.194802Z","iopub.execute_input":"2022-07-26T04:27:07.195596Z","iopub.status.idle":"2022-07-26T04:27:07.525773Z","shell.execute_reply.started":"2022-07-26T04:27:07.195538Z","shell.execute_reply":"2022-07-26T04:27:07.524589Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The distribution looks to be much more in line with what we would expect, and we also have created a new column to tell the model that these values were originally anomalous (because we will have ot fill in the nans with some value, probably the median of the column). The other columns with DAYS in the dataframe look to be about what we expect with no obvious outliers.\n\nAs an extremely important note, anything we do to the training data we also have to do to the testing data. Let's make sure to create the new column and fill in the existing column with np.nan in the testing data.","metadata":{}},{"cell_type":"code","source":"app_test['DAYS_EMPLOYED_ANOM'] = app_test['DAYS_EMPLOYED'] == 365243\napp_test['DAYS_EMPLOYED'].replace({365243: np.nan}, inplace= True)\n\nprint('There are %d anomalies in the test data out of %d entries' % (app_test['DAYS_EMPLOYED_ANOM'].sum(), len(app_test)))","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:07.527608Z","iopub.execute_input":"2022-07-26T04:27:07.529081Z","iopub.status.idle":"2022-07-26T04:27:07.545544Z","shell.execute_reply.started":"2022-07-26T04:27:07.529029Z","shell.execute_reply":"2022-07-26T04:27:07.544181Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Correlations\n\nNow that we have dealt with the categorical variables and the outliers, let's continue with the EDA. One way to try and understand the data is by looking for correlations between the features and the target. We can calculate the Pearson correlation coefficient between every variable and the target using the .corr dataframe method.\n\nThe correlation coefficient is not hte greatest method to represent \"relevance\" of a feature, but it does us an idea of possible relationships within the data. Some [general interpretations of the absolute value of the correlation coefficient](http://www.statstutor.ac.uk/resources/uploaded/pearsons.pdf) are:\n\n- .00-.19 “very weak”\n- .20-.39 “weak”\n- .40-.59 “moderate”\n- .60-.79 “strong”\n- .80-1.0 “very strong”","metadata":{}},{"cell_type":"code","source":"# Find correlation with the target and sort\ncorrelations = app_train.corr()['TARGET'].sort_values()\n\n# Display correlations\nprint('Most Postive Correlations:\\n', correlations.tail(15))\nprint('\\nMost Negative Correlations:\\n', correlations.head(15))","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:27:07.547800Z","iopub.execute_input":"2022-07-26T04:27:07.548293Z","iopub.status.idle":"2022-07-26T04:28:00.126101Z","shell.execute_reply.started":"2022-07-26T04:27:07.548258Z","shell.execute_reply":"2022-07-26T04:28:00.124217Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Let's take a look at some of more significant correlations: the DAYS_BIRTH is the most positive correlation. (except for TARGET because the correlation of a variable with itself is always 1!) Looking at the documnetation, DAYS_BIRTH is the age in days of the client at the time of the loan in negative days (for whatever reason!). The correlation is positive, but the values of this feature is actually negative, meaning that as the client gets older, they are less likely to default on their loan (ie. the target == 0). That's a little confusing, so we will take the absolute value of the feature and then the correlation will be negative.","metadata":{}},{"cell_type":"markdown","source":"### Effect of Age on Repayment","metadata":{}},{"cell_type":"code","source":"# Find the correlation of the positive days since birth and target\napp_train['DAYS_BIRTH'] = abs(app_train['DAYS_BIRTH'])\napp_train['DAYS_BIRTH'].corr(app_train['TARGET'])","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:00.128521Z","iopub.execute_input":"2022-07-26T04:28:00.129010Z","iopub.status.idle":"2022-07-26T04:28:00.149870Z","shell.execute_reply.started":"2022-07-26T04:28:00.128953Z","shell.execute_reply":"2022-07-26T04:28:00.148502Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As the client gets older, there is a negative linear relationship with the target meaning that a sclients get older, they tend to repay their loans on time more often.\n\nLet's start looking at this variable. First, we can make a histogram of the age. We will put the x axis in years to make the plot a little more understandable.","metadata":{}},{"cell_type":"code","source":"# Set the style of plots\nplt.style.use('fivethirtyeight')\n\n# Plot the distribution of ages if years\nplt.hist(app_train['DAYS_BIRTH'] / 365, edgecolor = 'k', bins = 25)\nplt.title('Age of Client')\nplt.xlabel('Age (years)')\nplt.ylabel('Count');","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:00.151358Z","iopub.execute_input":"2022-07-26T04:28:00.151672Z","iopub.status.idle":"2022-07-26T04:28:00.419670Z","shell.execute_reply.started":"2022-07-26T04:28:00.151643Z","shell.execute_reply":"2022-07-26T04:28:00.418490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"By itself, the distribution of age dose not tell us much other than that tere are no outliers as all the ages are reasonalbe. To visualize the effect of the age on the target, we will next make a [kernel density estimation plot (KDE)](https://en.wikipedia.org/wiki/Kernel_density_estimation) colored by the value of target. A [kernel density estimate plot shows the distribution of a single variabe](https://chemicalstatistician.wordpress.com/2013/06/09/exploratory-data-analysis-kernel-density-estimation-in-r-on-ozone-pollution-data-in-new-york-and-ozonopolis/) and can be thought of as a smoothed histogram (it is created by computing a kernel, usually a Gaussian, at each data point and then averaging all the individual kernels to develop a single smooth curve). We will use the seaborn kdeplot for this graph.","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (10, 8))\n\n# KDE plot of loans that were repaid on time\nsns.kdeplot(app_train.loc[app_train['TARGET'] == 0, 'DAYS_BIRTH'] / 365, label = 'target == 0')\n\n# KDE plot of loans which were not repid on time\nsns.kdeplot(app_train.loc[app_train['TARGET'] == 1, 'DAYS_BIRTH'] / 365, label = 'target == 1')\n\n# Labeling of plot\nplt.legend()\nplt.xlabel('Age (years)')\nplt.ylabel('Density')\nplt.title('Distribution of Ages');","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:00.423770Z","iopub.execute_input":"2022-07-26T04:28:00.426041Z","iopub.status.idle":"2022-07-26T04:28:01.836801Z","shell.execute_reply.started":"2022-07-26T04:28:00.425997Z","shell.execute_reply":"2022-07-26T04:28:01.835899Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The target == 1 curve skews towards the younger and end of the range. Although this is not a significant correlation (-0.07 correlation coefficient), this variable is likely going to be useful in a machine learning model because it does affect the target. Let's look at this relationship in another way: average failure to repay loans by age bracket.\n\nTo make this graph, first we cut the age category into bins 5 years each. Then, for each bin, we calculate the average value of the target, which tells us the ratio of loans that were not repaid in each age category.","metadata":{}},{"cell_type":"code","source":"# Age information in to a seperate dataframe\nage_data = app_train[['TARGET', 'DAYS_BIRTH']]\nage_data['YEARS_BIRTH'] = age_data['DAYS_BIRTH'] / 365\n\n# Bin the age data\nage_data['YEARS_BINNED'] = pd.cut(age_data['YEARS_BIRTH'], bins = np.linspace(20, 70, num = 11))\nage_data.head(10)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:01.838118Z","iopub.execute_input":"2022-07-26T04:28:01.838618Z","iopub.status.idle":"2022-07-26T04:28:02.039177Z","shell.execute_reply.started":"2022-07-26T04:28:01.838588Z","shell.execute_reply":"2022-07-26T04:28:02.037904Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Group by the bin and calculate averages\nage_groups = age_data.groupby('YEARS_BINNED').mean()\nage_groups","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:02.040908Z","iopub.execute_input":"2022-07-26T04:28:02.041582Z","iopub.status.idle":"2022-07-26T04:28:02.072476Z","shell.execute_reply.started":"2022-07-26T04:28:02.041533Z","shell.execute_reply":"2022-07-26T04:28:02.071330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize= (8, 8))\n\n# Graph the age bins and the average of the target as a bar plot\nplt.bar(age_groups.index.astype(str), 100 * age_groups['TARGET'])\n\n# Plot labeling\nplt.xticks(rotation = 75)\nplt.xlabel('Age Group (years)')\nplt.ylabel('Failure to Repay (%)')\nplt.title('Failure to Repay by Age Group');","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:02.074099Z","iopub.execute_input":"2022-07-26T04:28:02.075043Z","iopub.status.idle":"2022-07-26T04:28:02.324518Z","shell.execute_reply.started":"2022-07-26T04:28:02.075004Z","shell.execute_reply":"2022-07-26T04:28:02.323281Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"There is a clear trend: younger applicants are more likely to not repay the loan! The rate of failure to repay is above 10% for the youngest three age groups and below 5% for the oldest age group.\n\nThis is information that could be directly used bt the bank: because younger clients are less likely to repay the loan, maybe they should be provided with more guidance or financial planning tips. This dies not mean the bank should discriminate against younger clients, but it would be smart to take precautionary measures to help younger clients pay on time.","metadata":{}},{"cell_type":"markdown","source":"### Exterior Sources\n\nThe 3 variables with the strongest negative correlations with the target are EXT_SOURCE_1, EXT_SOURCE_2, and EXT_SOURCE_3. According to the documentation, these features represent a \"normalized score from external data source\". I'm not sure what this exactly means, but it may be a cumulative sort of credit rating made using numerous source of data\n\nLet's take a look at these variables.\n\nFirst, we can show the correlations of the EXT_SOURCE feature with the target and with each other.","metadata":{}},{"cell_type":"code","source":"# Extract the EXT_SOURCE variables and show coreelations\next_data = app_train[['TARGET', 'EXT_SOURCE_1', 'EXT_SOURCE_2', 'EXT_SOURCE_3', 'DAYS_BIRTH']]\next_data_corrs = ext_data.corr()\next_data_corrs","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:02.326553Z","iopub.execute_input":"2022-07-26T04:28:02.327433Z","iopub.status.idle":"2022-07-26T04:28:02.389028Z","shell.execute_reply.started":"2022-07-26T04:28:02.327381Z","shell.execute_reply":"2022-07-26T04:28:02.387966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize = (8, 6))\n\n# Heatmap of correlations\nsns.heatmap(ext_data_corrs, cmap = plt.cm.RdYlBu_r, vmin = -0.25, annot = True, vmax = 0.6)\nplt.title('Correlation Heatmap');","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:02.390533Z","iopub.execute_input":"2022-07-26T04:28:02.391527Z","iopub.status.idle":"2022-07-26T04:28:02.759591Z","shell.execute_reply.started":"2022-07-26T04:28:02.391488Z","shell.execute_reply":"2022-07-26T04:28:02.758171Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"All three EXT_SOURCE featureshave negative correlations with the target, indicating that as the value of the EXT_SOURCE increases, the clients is more likely to repay the loan. We can also see that DAYS_BIRTH is positively correlated with EXT_SOURCE_1 indicating that maybe one of  the factors in this score is the client age.\n\nNext we can look at the distribution of each of these features colored by the valeu of the target. This will let us visualize the effect of this variabel on the target.","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (10, 12))\n\n# iterate through the sources\n\nfor i, source in enumerate(['EXT_SOURCE_1', 'EXT_SOURCE_2', 'EXT_SOURCE_3']):\n    \n    # Create a new subplot for each source\n    plt.subplot(3, 1, i + 1)\n    # Plot repaid loans\n    sns.kdeplot(app_train.loc[app_train['TARGET'] == 0, source], label = 'target == 0')\n    # Plot loans that were not repaid\n    sns.kdeplot(app_train.loc[app_train['TARGET'] == 1, source], label = 'target == 1')\n    \n    # Label the plot\n    plt.title('Distribution of %s by Target Value' % source)\n    plt.xlabel('%s' % source); plt.ylabel('Density');\n    plt.legend();\n    \nplt.tight_layout(h_pad = 2.5)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:02.761309Z","iopub.execute_input":"2022-07-26T04:28:02.761839Z","iopub.status.idle":"2022-07-26T04:28:06.213071Z","shell.execute_reply.started":"2022-07-26T04:28:02.761797Z","shell.execute_reply":"2022-07-26T04:28:06.211810Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"EXT_SOURCE_3 displays the greatest difference between the values of  the target. We can clearly see that this feature has some relationship to the likelihood of an applicant to repay a loan. The relationship is not very strong (in fact they are all considered very weak, but these variables will still be useful for a machine learning model to predict whether or not an applicant will repay a loan on time.","metadata":{}},{"cell_type":"markdown","source":"### Pairs Plot\n\nAs a final exploratory plot, we can make a pairs plot of the EXT_SOURCE variables and the DAYS_BIRTH variable. The Pairs Plot is a great exploration tool because it lets us see relationships between multiple pairs of variables as well as distributions of single variables. Here we are using the seaborn visualization library and the PairGrid function to create a Pairs Plot with scatterplots on the upper triangle, histograms on the diagonal, and 2D kernel density plots and correlation coefficent on the lower triangle.\n\nIf you don't understand this code, that's all right! Plotting in Python can be overly complex, and for anything beyound the simplest graphs, I usually find an existing implementation and adapt the code (don't repeat yourself)!","metadata":{}},{"cell_type":"code","source":"# Copy the data for plotting\nplot_data = ext_data.drop(columns = ['DAYS_BIRTH']).copy()\n\n# Add in the age of the client in years\nplot_data['YEARS_BIRTH'] = age_data['YEARS_BIRTH']\n\n# Drop na values and limit to first 100000 rows\nplot_data = plot_data.dropna().loc[:100000, :]\n\n# Function to calculate correlation coefficient between two columns\ndef corr_func(x, y, **kwargs):\n    r = np.corrcoef(x, y)[0][1]\n    ax = plt.gca()\n    ax.annotate(\"r = {:.2f}\".format(r),\n                xy=(.2, .8), xycoords=ax.transAxes,\n                size = 20)\n\n# Create the pairgrid object\ngrid = sns.PairGrid(data = plot_data, size = 3, diag_sharey=False,\n                    hue = 'TARGET', \n                    vars = [x for x in list(plot_data.columns) if x != 'TARGET'])\n\n# Upper is a scatter plot\ngrid.map_upper(plt.scatter, alpha = 0.2)\n\n# Diagonal is a histogram\ngrid.map_diag(sns.kdeplot)\n\n# Bottom is density plot\ngrid.map_lower(sns.kdeplot, cmap = plt.cm.OrRd_r);\n\nplt.suptitle('Ext Source and Age Features Pairs Plot', size = 32, y = 1.05);","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:28:06.215031Z","iopub.execute_input":"2022-07-26T04:28:06.215408Z","iopub.status.idle":"2022-07-26T04:30:13.957198Z","shell.execute_reply.started":"2022-07-26T04:28:06.215374Z","shell.execute_reply":"2022-07-26T04:30:13.955880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In this plot, the red indicate loans that were not repaid and the blue are loans are paid. We can see the different relationships within the data. These does appear to be a moderate positive linear relationship between the EXT_SOURCE_1 and the DAYS_BIRTH (or equivalently YEARS_BIRHT), indication that this feature may take in to account the age of the client.","metadata":{}},{"cell_type":"code","source":"# Copy the data for plotting\nplot_data = ext_data.drop(columns = ['DAYS_BIRTH']).copy()\n\n# Add in the age of the client in years\nplot_data['YEARS_BIRTH'] = age_data['YEARS_BIRTH']\n\n# Drop na values and limit to first 100000 rows\nplot_data = plot_data.dropna().loc[:100000, :]\n\n# Function to calculate correlation coefficient between two columns\ndef corr_func(x, y, **kwargs):\n    r = np.corrcoef(x, y)[0][1]\n    ax = plt.gca()\n    ax.annotate(\"r = {:.2f}\".format(r),\n                xy=(.5, .5), xycoords=ax.transAxes,\n                size = 20)\n\n# Create the pairgrid object\ngrid = sns.PairGrid(data = plot_data, size = 3, diag_sharey=False,\n                    hue = 'TARGET', \n                    vars = [x for x in list(plot_data.columns) if x != 'TARGET'])\n\n# Upper is a scatter plot\ngrid.map_upper(plt.scatter, alpha = 0.2)\n\n# Diagonal is a histogram\ngrid.map_diag(sns.kdeplot)\n\n# Bottom is density plot\ngrid.map_lower(sns.kdeplot, cmap = plt.cm.OrRd_r);\n\nplt.suptitle('Ext Source and Age Features Pairs Plot', size = 32, y = 1.05);","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:30:13.959335Z","iopub.execute_input":"2022-07-26T04:30:13.960378Z","iopub.status.idle":"2022-07-26T04:32:20.215014Z","shell.execute_reply.started":"2022-07-26T04:30:13.960326Z","shell.execute_reply":"2022-07-26T04:32:20.213787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Engineering\n\nKaggle competitions are won by feature engineering: those win are those can create that most useful features out of the data. (This is true for the most part as the winning models, at least for structured data, all tend to be variants on [gradient boosting](http://blog.kaggle.com/2017/01/23/a-kaggle-master-explains-gradient-boosting/)). This represents one of the patterns in machine learning: feature engineering has a greater return on investment than model building and hyperparameter tuning. [This is a great article on the subject](https://www.featurelabs.com/blog/secret-to-data-science-success/). As Andrew Ng is fond of saying: \"applied machine learning is basically feature engineering.\n\nWhile choosing the right model and optimal settings are important, the model can only learn from the data it is given. Making sure this data is as relevant to the task as possible is the job of the data scientist (and maybe some [automated tools](https://docs.featuretools.com/getting_started/install.html) to help us out).\n\nFeature engineering refers to a geneal process and can involve both feature construction: adding new features from the existing data, and feature selection: choosing only the most important features or other methods of dimensionality reduction. There are many techniques we can use to both create features and select features.\n\nWe will do a lot of feature engineering when we start using the other data sources, but in this notebook we will try only two simple feauture construction methods:\n\n- Polynomial features\n- Domain knowledge features","metadata":{}},{"cell_type":"markdown","source":"## Polynomial Features\n\nOne simple feature construction method is called [polynomial features](http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.PolynomialFeatures.html). In this method, we make features that are power of existing features as well as interaction terms between existing features. For example, we can create variables EXT_SOURCE_1^2 and EXT_SOURCE_2^2 and also variables such as EXT_SOURCE_1 * EXT_SOURCE_2, EXT_SOURCE_1 * EXT_SOURCE_2^2, EXT_SOURCE_1^2 x EXT_SOURCE_2^2, and so on. These features that are a combination of multiple individual variables are called [interaction terms](https://en.wikipedia.org/wiki/Interaction_(statistics) because they capture the interactions between variables. In other words, while two variables by themselves may not have a strong influence ao the target, combining them together into a single interaction variable might show a relationship with the target. [Interaction terms are commonly used in statistical models](https://www.theanalysisfactor.com/interpreting-interactions-in-regression/) to capture the effects of multiple variables, but I do not see them used as often in machine learning. Nonetheless, we can try out a few to see if they might help our model to predict whether or not a client will repay a loan.\n\nJake VanderPlas writes about [ploynomial features in his excellent book Python for Data Science](https://jakevdp.github.io/PythonDataScienceHandbook/05.04-feature-engineering.html) for those who want more information.\n\nIn the following code, we create polynomial features using the EXT_SOURCE variables and the DAYS_BIRTH variable. [Scikit-Learn](http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.PolynomialFeatures.html) has a useful class called PolynomialFeatures that creates the polynomials and the interaction terms up to a specified degree. We can use a degree of 3 to see the results (when we are creating polynomial features, we want to avoid using too high of a degree, both because the number of features scales exponentially with the degree, and because we can run into [problems with overfitting](http://scikit-learn.org/stable/auto_examples/model_selection/plot_underfitting_overfitting.html#sphx-glr-auto-examples-model-selection-plot-underfitting-overfitting-py)).","metadata":{}},{"cell_type":"code","source":"# Make a new dataframe for polynomial features\npoly_features = app_train[['EXT_SOURCE_1', 'EXT_SOURCE_2', 'EXT_SOURCE_3', 'DAYS_BIRTH', 'TARGET']]\npoly_features_test = app_test[['EXT_SOURCE_1', 'EXT_SOURCE_2', 'EXT_SOURCE_3', 'DAYS_BIRTH']]\n\n# imputer for handling missing values\nfrom sklearn.impute import SimpleImputer\nimputer = SimpleImputer(strategy=\"median\")\n\npoly_target = poly_features['TARGET']\n\npoly_features = poly_features.drop(columns = ['TARGET'])\n\n# Need to impute missing valeus\npoly_features = imputer.fit_transform(poly_features)\npoly_features_test = imputer.transform(poly_features_test)\n\nfrom sklearn.preprocessing import PolynomialFeatures\n\n# Create the polynomial object with specified degree\npoly_transformer = PolynomialFeatures(degree = 3)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:20.216418Z","iopub.execute_input":"2022-07-26T04:32:20.216746Z","iopub.status.idle":"2022-07-26T04:32:20.633279Z","shell.execute_reply.started":"2022-07-26T04:32:20.216699Z","shell.execute_reply":"2022-07-26T04:32:20.632102Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Train the polynomial features\npoly_transformer.fit(poly_features)\n\n# Transform the features\npoly_features = poly_transformer.transform(poly_features)\npoly_features_test = poly_transformer.transform(poly_features_test)\nprint('Polynomial Features shape: ', poly_features.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:20.634753Z","iopub.execute_input":"2022-07-26T04:32:20.635165Z","iopub.status.idle":"2022-07-26T04:32:20.814961Z","shell.execute_reply.started":"2022-07-26T04:32:20.635131Z","shell.execute_reply":"2022-07-26T04:32:20.813763Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This creates a considerable number of new features. To get the names we have to use the polynomial features get_feature_names method.","metadata":{}},{"cell_type":"code","source":"poly_transformer.get_feature_names(input_features = ['EXT_SOURCE_1', 'EXT_SOURCE_2',\n                                                     'EXT_SOURCE_3', 'DAYS_BIRTH'])[:15]","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:20.816373Z","iopub.execute_input":"2022-07-26T04:32:20.816685Z","iopub.status.idle":"2022-07-26T04:32:20.825523Z","shell.execute_reply.started":"2022-07-26T04:32:20.816655Z","shell.execute_reply":"2022-07-26T04:32:20.824352Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"There are 35 features with individual features raised to powers up to degree 3 and interaction terms. Now, we can see whether any of these new features anre correlated with the target.","metadata":{}},{"cell_type":"code","source":"# Create a dataframe of the features\npoly_features = pd.DataFrame(poly_features, \n                            columns = poly_transformer.get_feature_names([\n                                'EXT_SOURCE_1', 'EXT_SOURCE_2','EXT_SOURCE_3', 'DAYS_BIRTH'\n                            ]))\n\n# Add in the target\npoly_features['TARGET'] = poly_target\n\n# Find the correlations with the target\npoly_corrs = poly_features.corr()['TARGET'].sort_values()\n\n# Display most negative and most positive\nprint(poly_corrs.head(10), '\\n')\nprint(poly_corrs.tail(5))","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:20.827360Z","iopub.execute_input":"2022-07-26T04:32:20.827744Z","iopub.status.idle":"2022-07-26T04:32:22.091383Z","shell.execute_reply.started":"2022-07-26T04:32:20.827686Z","shell.execute_reply":"2022-07-26T04:32:22.090208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Several of the new variables have a greater (in terms of absolute magnitude) correlation with the target than the original features. When we build machine learning models, we can try with and without these features to determine if they actually help the model learn.\n\nWe all add these features to a copy of the training and testing data and then evaluate models with and without the features. Many times in machine learning, the only way to know if an approach will work is to try it out!","metadata":{}},{"cell_type":"code","source":"# Put test features into dataframe\npoly_features_test = pd.DataFrame(poly_features_test,\n                                 columns = poly_transformer.get_feature_names(\n                                 ['EXT_SOURCE_1', 'EXT_SOURCE_2','EXT_SOURCE_3', 'DAYS_BIRTH'])\n                                 )\n\n# Merge polynomial features into training dataframe\npoly_features['SK_ID_CURR'] = app_train['SK_ID_CURR']\napp_train_poly = app_train.merge(poly_features, on= 'SK_ID_CURR', how = 'left')\n\n# Merge polynomial features into testing dataframe\npoly_features_test['SK_ID_CURR'] = app_test['SK_ID_CURR']\napp_test_poly = app_test.merge(poly_features_test, on = 'SK_ID_CURR', how = 'left')\n\n# Align the dataframes\napp_train_poly, app_test_poly = app_train_poly.align(app_test_poly, join= 'inner', axis= 1)\n\n# Print out the new shapes\nprint('Training data with polynomial features shape: ', app_train_poly.shape)\nprint('Tseting data with polynomial features shape: ', app_test_poly.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:22.093050Z","iopub.execute_input":"2022-07-26T04:32:22.093740Z","iopub.status.idle":"2022-07-26T04:32:24.462400Z","shell.execute_reply.started":"2022-07-26T04:32:22.093675Z","shell.execute_reply":"2022-07-26T04:32:24.460451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Domain Knowledge Features\n\nMaybe it's not entirely correct to call this \"domain knowledge\" because I'm not a credit expert, but perhaps we could call this \"attempts at applying limited financial knowledge\". In this frame of mind, we can make a couple features that to capture what we think may be important for telling whether a client will default on a loan. Here I'm going to use five features that were inspired by [this script](https://www.kaggle.com/jsaguiar/updated-0-792-lb-lightgbm-with-simple-features) by Aguiar:\n\n- CREDIT_INCOME_PERCENT : the percentage of the credit amount relative to a client's income\n- ANNUITY_INCOME_PERCNET : the percentage of the loan annuity relative to a client's income\n- CREDIT_TERM :  the length of the payment in months (since the annuity is the monthly amount due)\n- DAYS_EMPLOYED_PERCENT : the percentage of  the days employed relative to the clients' age\n\nAgain, thanks to Aguiar and [his great script](https://www.kaggle.com/jsaguiar/updated-0-792-lb-lightgbm-with-simple-features) for exploring these features.","metadata":{}},{"cell_type":"code","source":"app_train_domain = app_train.copy()\napp_test_domain = app_test.copy()\n\napp_train_domain['CREDIT_INCOME_PERCENT'] = app_train_domain['AMT_CREDIT'] / app_train_domain['AMT_INCOME_TOTAL']\napp_train_domain['ANNUITY_INCOME_PERCENT'] = app_train_domain['AMT_ANNUITY'] / app_train_domain['AMT_INCOME_TOTAL']\napp_train_domain['CREDIT_TERM'] = app_train_domain['AMT_ANNUITY'] / app_train_domain['AMT_CREDIT']\napp_train_domain['DAYS_EMPLOYED_PERCENT'] = app_train_domain['DAYS_EMPLOYED'] / app_train_domain['DAYS_BIRTH']","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:24.468833Z","iopub.execute_input":"2022-07-26T04:32:24.469241Z","iopub.status.idle":"2022-07-26T04:32:24.630435Z","shell.execute_reply.started":"2022-07-26T04:32:24.469207Z","shell.execute_reply":"2022-07-26T04:32:24.628998Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"app_test_domain['CREDIT_INCOME_PERCENT'] = app_test_domain['AMT_CREDIT'] / app_test_domain['AMT_INCOME_TOTAL']\napp_test_domain['ANNUITY_INCOME_PERCENT'] = app_test_domain['AMT_ANNUITY'] / app_test_domain['AMT_INCOME_TOTAL']\napp_test_domain['CREDIT_TERM'] = app_test_domain['AMT_ANNUITY'] / app_test_domain['AMT_CREDIT']\napp_test_domain['DAYS_EMPLOYED_PERCENT'] = app_test_domain['DAYS_EMPLOYED'] / app_test_domain['DAYS_BIRTH']","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:24.632355Z","iopub.execute_input":"2022-07-26T04:32:24.633793Z","iopub.status.idle":"2022-07-26T04:32:24.646943Z","shell.execute_reply.started":"2022-07-26T04:32:24.633740Z","shell.execute_reply":"2022-07-26T04:32:24.646018Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualize New Variables\n\nWe should explore these **domain knowledge** variables visually in a graph. For all of these, we will make the same KDE plot colored by the value of the TARGET.","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize= (12,20))\n# iterate through the new features\nfor i, feature in enumerate(['CREDIT_INCOME_PERCENT', 'ANNUITY_INCOME_PERCENT',\n                             'CREDIT_TERM', 'DAYS_EMPLOYED_PERCENT']):\n    \n    # Create a new subplot for each source\n    plt.subplot(4, 1, i + 1)\n    # Plot repaid loans\n    sns.kdeplot(app_train_domain.loc[app_train_domain['TARGET'] == 0, feature], label = 'target == 0')\n    # Plot loans that were not repaid\n    sns.kdeplot(app_train_domain.loc[app_train_domain['TARGET'] == 1, feature], label = 'target == 1')\n    \n    # Label the plots\n    plt.title('Distribution of %s by Target Value' % feature)\n    plt.legend()\n    plt.xlabel('%s' % feature)\n    plt.ylabel('Density');\n    \nplt.tight_layout(h_pad = 2.5)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:24.649060Z","iopub.execute_input":"2022-07-26T04:32:24.649647Z","iopub.status.idle":"2022-07-26T04:32:30.625304Z","shell.execute_reply.started":"2022-07-26T04:32:24.649549Z","shell.execute_reply":"2022-07-26T04:32:30.624052Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"It's hard to say ahead of time if these new features will be useful. The only way to tell for sure is to try them out!","metadata":{}},{"cell_type":"markdown","source":"# Baseline\n\nFor a naive baseline, we could guess the same value for all examples on the testing set. We are asked to predict the probability of not repaying the loan, so if we are entirely unsure, we would guress 0.5 for all observations on the test set. This will get us a Reciever Operating Characteristic Area Under the Curve (AUC ROC) of 0.5 in the competition ([random guessing on a classification task will score a 0.5](https://stats.stackexchange.com/questions/266387/can-auc-roc-be-between-0-0-5)).\n\nSince we already know score we are going to get, we don't really need to make a navie baseline guess. Let's use a slightly more sophisticated model for our actual baseline: Logistic Regression.","metadata":{}},{"cell_type":"markdown","source":"## Logistic Regression Implementation\n\nHere I will focus on implementing the model rather than explaining the details, but for those who want to learn more about the theory of machine learning algorithms, I recommend both [An Introduction to Statisical Learning](http://www-bcf.usc.edu/~gareth/ISL/) and [Hands-On Machine Learning with Scikit-Learn and TensorFlow](http://shop.oreilly.com/product/0636920052289.do). Both of these books present the theory and also  the code needed to make the models (in R and Python respectively). They both teach with the mindset that the best way to learn is by doing, and they are very effective!\n\nTo get a baseline, we will use all of the features after encoding the categorical variables. We will preprocess the data by filling in the missing values (imputation) and normalizing the range of the features( features scaling). The following code performs both of these preprocessing steps.","metadata":{}},{"cell_type":"code","source":"from sklearn.preprocessing import MinMaxScaler\nfrom sklearn.impute import SimpleImputer\n\n# Drop the target from the training data\nif 'TARGET' in app_train:\n    train = app_train.drop(columns = ['TARGET'])\nelse:\n    train = app_train.copy()\n    \n# Feature names\nfeatures = list(train.columns)\n\n# Copy of the testing data\ntest = app_test.copy()\n\n# Median imputation of missing values\nimputer = SimpleImputer(strategy = 'median')\n\n# Scale each feature to 0-1\nscaler = MinMaxScaler(feature_range = (0, 1))\n\n# Fit on the training data\nimputer.fit(train)\n\n# Transform both training and testing data\ntrain = imputer.transform(train)\ntest = imputer.transform(app_test)\n\n# Repeat with the scaler\nscaler.fit(train)\ntrain = scaler.transform(train)\ntest = scaler.transform(test)\n\nprint('Training data shape: ', train.shape)\nprint('Testing data shape: ', test.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:32:30.626814Z","iopub.execute_input":"2022-07-26T04:32:30.627295Z","iopub.status.idle":"2022-07-26T04:33:13.832123Z","shell.execute_reply.started":"2022-07-26T04:32:30.627259Z","shell.execute_reply":"2022-07-26T04:33:13.831002Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We will use LogisticRegression from [Scikit-Learn](http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) for our first model. The only change we will make from default model settings is to lower the [regularization parameter](http://scikit-learn.org/stable/modules/linear_model.html#logistic-regression). C, which controls the amount of overfitting (a lower value should decrease overfitting). This will get us slightly better results than the default LogisticRegression, but it still will set a low bar for any future models.\n\nHere we use the familiar Scikit-Learn modeling syntax: we first create the model, then we train the model using .fit and then we make predictions on the testing data using .predict_proba (remember that we want probabilities and not a 0 or 1).","metadata":{}},{"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\n\n# Make the model with the specified regularization parameter\nlog_reg = LogisticRegression(C = 0.0001)\n\n# Train on the training data\nlog_reg.fit(train, train_labels)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:33:13.833652Z","iopub.execute_input":"2022-07-26T04:33:13.833991Z","iopub.status.idle":"2022-07-26T04:33:16.861322Z","shell.execute_reply.started":"2022-07-26T04:33:13.833961Z","shell.execute_reply":"2022-07-26T04:33:16.854356Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Now that the model has benn trained, we can use it to make predictions. We want to predict the probabilities of not paying a loan, so we use the model predict.proba method. This returns an m x 2 array where m is the number of observations. The first column is the probability of the target being 0 and the second column is the probability of  the target being 1 (so for a single row, the two columns must sum to 1). We want the probability the loan is not repaid, so we will select the second column.\n\nThe following code makes the predictions and selects the correct column.","metadata":{}},{"cell_type":"code","source":"# Make predictions\n# Make sure to select the second column only\nlog_reg_pred = log_reg.predict_proba(test)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:33:16.862971Z","iopub.execute_input":"2022-07-26T04:33:16.863654Z","iopub.status.idle":"2022-07-26T04:33:16.895161Z","shell.execute_reply.started":"2022-07-26T04:33:16.863597Z","shell.execute_reply":"2022-07-26T04:33:16.893995Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The predictions must be in the format shown in the sample_submission.csv file, where there are only two columns: SK_ID_CURR and TARGET. We will create a dataframe in this format from the test set and thes predictions called submit.","metadata":{}},{"cell_type":"code","source":"# Submission dataframe\nsubmit = app_test[['SK_ID_CURR']]\nsubmit['TARGET'] = log_reg_pred\n\nsubmit.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:33:16.900389Z","iopub.execute_input":"2022-07-26T04:33:16.901254Z","iopub.status.idle":"2022-07-26T04:33:16.930047Z","shell.execute_reply.started":"2022-07-26T04:33:16.901200Z","shell.execute_reply":"2022-07-26T04:33:16.928793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Save the submission to a csv file\nsubmit.to_csv('log_reg_baseline.csv', index = False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:33:16.936361Z","iopub.execute_input":"2022-07-26T04:33:16.937509Z","iopub.status.idle":"2022-07-26T04:33:17.152555Z","shell.execute_reply.started":"2022-07-26T04:33:16.937446Z","shell.execute_reply":"2022-07-26T04:33:17.151128Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The submission has now been saved  to the virtual environment in which our notebook is running. To access the submission, at the end of the notebook, we will hit the blue Commint & Run button at the upper right of  the kernel. This runs the entire notebook and then leys us download any files that are created during the run.\n\nOnce we run the notebook, the files vrreated are available in the Versions tab under the Output sub-tab. From here, the submission files can be submitted to the competition or downloaded. Since there are several models in this notebook, there will be multiple output files.\n\n**The logistic regression baseline should scroe around 0.671 when submitted.**","metadata":{}},{"cell_type":"markdown","source":"# Improved Model: Random Forest\n\nTo try and beat the poor performance of our baseline, we can update the algorithm. Let's try using a Random Forest on the same training data to see how that affects performance. The Random Forest is a much more powerful model especially when we use hundreds of trees. We will use 100 trees in the random forest.","metadata":{}},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\n\n# Make the random forest classifier\nrandom_forest = RandomForestClassifier(n_estimators = 100, random_state = 50, verbose = 1, n_jobs = -1)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:33:17.154069Z","iopub.execute_input":"2022-07-26T04:33:17.154526Z","iopub.status.idle":"2022-07-26T04:33:17.251395Z","shell.execute_reply.started":"2022-07-26T04:33:17.154481Z","shell.execute_reply":"2022-07-26T04:33:17.250255Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Train on the training data\nrandom_forest.fit(train, train_labels)\n\n# Extract feature importances\nfeature_importance_values = random_forest.feature_importances_\nfeature_importances = pd.DataFrame({'feature' : features, 'importance': feature_importance_values})\n\n# Make predictions on the test data\npredictions = random_forest.predict_proba(test)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:33:17.252756Z","iopub.execute_input":"2022-07-26T04:33:17.253098Z","iopub.status.idle":"2022-07-26T04:34:31.219237Z","shell.execute_reply.started":"2022-07-26T04:33:17.253068Z","shell.execute_reply":"2022-07-26T04:34:31.217111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Make a submission dataframe\nsubmit = app_test[['SK_ID_CURR']]\nsubmit['TARGET'] = predictions\n\n# Save the submission dataframe\nsubmit.to_csv('random_forest_baseline.csv', index = False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:34:31.221167Z","iopub.execute_input":"2022-07-26T04:34:31.221613Z","iopub.status.idle":"2022-07-26T04:34:31.343058Z","shell.execute_reply.started":"2022-07-26T04:34:31.221576Z","shell.execute_reply":"2022-07-26T04:34:31.341571Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"These predictions will also be available when we run the entire notebook.\n\n**This model should score around 0.678 when submitted.**","metadata":{}},{"cell_type":"markdown","source":"#### Make Predictions using Engineered Features\n\nThe only way to see if the Polynomial Features and Domain knowledge improved the model is to train a test a model on these features! We can then compare the submission performance to that for the model without these features to gauge the effect of our feature engineering.","metadata":{}},{"cell_type":"code","source":"poly_features_names = list(app_train_poly.columns)\n\n# Impute the polynomial features\nimputer = SimpleImputer(strategy = 'median')\n\npoly_features = imputer.fit_transform(app_train_poly)\npoly_features_test = imputer.transform(app_test_poly)\n\n# Scale the polynomial features\nsclaer = MinMaxScaler(feature_range = (0, 1))\n\npoly_features = scaler.fit_transform(poly_features)\npoly_features_test = scaler.transform(poly_features_test)\n\nrandom_forest_poly = RandomForestClassifier(n_estimators = 100, random_state = 50,\n                                           verbose = 1, n_jobs = -1)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:34:31.345071Z","iopub.execute_input":"2022-07-26T04:34:31.346191Z","iopub.status.idle":"2022-07-26T04:35:21.577447Z","shell.execute_reply.started":"2022-07-26T04:34:31.346149Z","shell.execute_reply":"2022-07-26T04:35:21.576268Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Train on the training data\nrandom_forest_poly.fit(poly_features, train_labels)\n\n# Make predictions on the test data\npredictions = random_forest_poly.predict_proba(poly_features_test)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:35:21.578821Z","iopub.execute_input":"2022-07-26T04:35:21.579143Z","iopub.status.idle":"2022-07-26T04:37:20.227866Z","shell.execute_reply.started":"2022-07-26T04:35:21.579112Z","shell.execute_reply":"2022-07-26T04:37:20.226876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Make a submission dataframe\nsubmit = app_test[['SK_ID_CURR']]\nsubmit['TARGET'] = predictions\n\n# Save the submission dataframe\nsubmit.to_csv('random_forest_baseline_engineered.csv', index= False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:37:20.228955Z","iopub.execute_input":"2022-07-26T04:37:20.229293Z","iopub.status.idle":"2022-07-26T04:37:20.366754Z","shell.execute_reply.started":"2022-07-26T04:37:20.229263Z","shell.execute_reply":"2022-07-26T04:37:20.365635Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This model scored 0.678 when submitted to the competition, exactly the same as that without the engineered features. Given these results, it does not appear that our feature construction helped in this case.","metadata":{}},{"cell_type":"markdown","source":"#### Testing Domain Features\n\nNow we can test the domain features we made by hand.","metadata":{}},{"cell_type":"code","source":"app_train_domain = app_train_domain.drop(columns = 'TARGET')\n\ndomain_features_names = list(app_train_domain.columns)\n\n# Impute the domainnomial features\nimputer = SimpleImputer(strategy = 'median')\n\ndomain_features = imputer.fit_transform(app_train_domain)\ndomain_features_test = imputer.transform(app_test_domain)\n\n# Scale the domainnomial feautres\nscaler = MinMaxScaler(feature_range = (0, 1))\n\ndomain_features = scaler.fit_transform(domain_features)\ndomain_features_test = scaler.transform(domain_features_test)\n\nrandom_forest_domain = RandomForestClassifier(n_estimators = 100,\n                                             random_state = 50,\n                                             verbose = 1,\n                                             n_jobs = -1)\n# Train on the training data\nrandom_forest_domain.fit(domain_features, train_labels)\n\n# Extract feature importances\nfeature_importance_values_domain = random_forest_domain.feature_importances_\nfeature_importance_domain = pd.DataFrame({'feature' : domain_features_names,\n                                          'importance': feature_importance_values_domain})\n\n# Make predictions on the test data\npredictions = random_forest_domain.predict_proba(domain_features_test)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:37:20.368049Z","iopub.execute_input":"2022-07-26T04:37:20.368344Z","iopub.status.idle":"2022-07-26T04:39:35.996514Z","shell.execute_reply.started":"2022-07-26T04:37:20.368316Z","shell.execute_reply":"2022-07-26T04:39:35.995509Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Make a submission dataframe\nsubmit = app_test[['SK_ID_CURR']]\nsubmit['TARGET'] = predictions\n\n# Save the submission dataframe\nsubmit.to_csv('random_forest_baseline_domain.csv', index= False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:39:35.997621Z","iopub.execute_input":"2022-07-26T04:39:35.997980Z","iopub.status.idle":"2022-07-26T04:39:36.126252Z","shell.execute_reply.started":"2022-07-26T04:39:35.997947Z","shell.execute_reply":"2022-07-26T04:39:36.125273Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This scores 0.679 when submitted which probably shows that the engineered features do not help in this model (however they do help in the Gradient Boosting Model at the end of the notebook).\n\nIn later notebooks, we will do more [feature engineering](https://docs.featuretools.com/index.html) by using the information from the other data source. From experience, this will definitely help our model!","metadata":{}},{"cell_type":"markdown","source":"### Model Interpretation: Feature Importances\n\nAs a simple method to see which variables are the most relevant, we can look at the feature importances of the random foreset. Given the correlations we saw in the exploratory data analysis, we should expect that the most important features are the EXT_SOURCE and the DAYS_BIRTH. We may use these feature importances as a method of dimensionality reduction in future work.","metadata":{}},{"cell_type":"code","source":" '''\n    Plot importances returned by a model. This can work with any measure of\n    feature importance prpvided that higher importance is better\n    \n    Args:\n        df (dataframe): feature importances. Must have the features in a column\n        called 'features' and the importance in a column called 'importance'\n        \n    Returns:\n        show a plot of the 15 most importance features\n        df (dataframe): feature importances sorted by importance (highest to lowest)\n        with a column for normalized importance\n    '''","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:39:36.127572Z","iopub.execute_input":"2022-07-26T04:39:36.128214Z","iopub.status.idle":"2022-07-26T04:39:36.136592Z","shell.execute_reply.started":"2022-07-26T04:39:36.128174Z","shell.execute_reply":"2022-07-26T04:39:36.135249Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_feature_importances(df):\n    # Sort features according to importance\n    df = df.sort_values('importance', ascending = False).reset_index()\n    \n    # Normalize the feature importances to add up to one\n    df['importance_normalized'] = df['importance'] / df['importance'].sum()\n    \n    # Make a horizontal bar chart of feature importances\n    plt.figure(figsize= (10, 6))\n    ax = plt.subplot()\n    \n    # Need to reverse the index to plot most important on top\n    ax.barh(list(reversed(list(df.index[:15]))),\n           df['importance_normalized'].head(15),\n           align = 'center', edgecolor = 'k')\n    \n    # Set the yticks and labels\n    ax.set_yticks(list(reversed(list(df.index[:15]))))\n    ax.set_yticklabels(df['feature'].head(15))\n    \n    # Plot labeling\n    plt.xlabel('Normalized Importance')\n    plt.title('Feature Importance')\n    plt.show()\n    \n    return df","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:39:36.138262Z","iopub.execute_input":"2022-07-26T04:39:36.138875Z","iopub.status.idle":"2022-07-26T04:39:36.149185Z","shell.execute_reply.started":"2022-07-26T04:39:36.138838Z","shell.execute_reply":"2022-07-26T04:39:36.148044Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Show the feautre importances for the default features\nfeature_importances_sorted = plot_feature_importances(feature_importances)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:39:36.150424Z","iopub.execute_input":"2022-07-26T04:39:36.151468Z","iopub.status.idle":"2022-07-26T04:39:36.450597Z","shell.execute_reply.started":"2022-07-26T04:39:36.151426Z","shell.execute_reply":"2022-07-26T04:39:36.449200Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As expected, the most important features are those dealing with EXT_SOURCE and DAYS_BIRTH. We see that there are only a handful of features with a significant importance to the model, which suggests we may be able to drop many of the features without a decrease in performance (and we may even see an increase in performance). Feautre importances are not the most sophisticated method to interpret a model or perform dimensionality reduction, but they let us start to understand what factors our model takes into account when it makes predictions.","metadata":{}},{"cell_type":"code","source":"feature_importances_domain_sorted = plot_feature_importances(feature_importance_domain)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:39:36.452211Z","iopub.execute_input":"2022-07-26T04:39:36.452934Z","iopub.status.idle":"2022-07-26T04:39:36.721075Z","shell.execute_reply.started":"2022-07-26T04:39:36.452884Z","shell.execute_reply":"2022-07-26T04:39:36.719939Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We see that all four of our hand-engineered features made it into the top 15 most important! \nThis should give us confidence that our domain knowledge was at least partially on track.","metadata":{}},{"cell_type":"markdown","source":"# Conclusions\n\nIn this notebook, we saw how to get started with a Kaggle machine learning competition. We first made sure to undeerstand the data, our task, and the metric by which our submissions will be judged. Then, we performed a fairly simple EDA to try and identify relationships, trends, or anmalies that may help our modeling. Along the way, we performed necessary preprocessing steps such as encoding categorical variables, imputing missing values, and scaling features to a range. Then, we constucted new features out of the existing data to see if doing so could help our model.\n\nOnce the data exploration, data preparation, and feature engineering was complete, we implemented a baseline model upon which we hope to improve. Then we built a second slightly more complicated model to beat our first score. We also carried out an experiment to determine the effect of adding  the engineering variables.\n\nWe followed the general outline of a [machine learning project](https://towardsdatascience.com/a-complete-machine-learning-walk-through-in-python-part-one-c62152f39420):\n\n- 1. Understand the problem and the data\n- 2. Data cleaning and formatting (this was mostly done for us)\n- 3. Exploratory Data Analysis\n- 4. Baseline model\n- 5. Improved model\n- 6. Model interpretation (just a little)\n\nMachine learning competitions do differ slightly from typical data sicence problems in that we are concerned only with achieving the best performance on a single metric and do not care about the interpretation. However, by attempting to understand how our models make decisions, we can try to improve them or examine the mistakes in order to correct the errors. In future notebooks we will look at incorporating more sources of data, building more complex models (by following the code of others), and improving our scores.\n\nI hope this notebook was able to get you up and running in this machine learning competition and that you are now ready to go out on your own - with help from the community - and start working on some great problems!\n\n**Running the notebook**: now that we are at the end of the notebook, you can hit the blue Commit & Run button to execute all the code at once. After the run is complete (this should take about 10 minutes), you can then access the files that were created by going to the versions tab and then the output sub-tab. The submission files can be directly submitted to the competition from this tab or they cna be downloaded to a local machine and saved. The final part is to share the share the notebook: go to the settings tab and change the visibility to Public. This allows the entire world to see your work!\n\n#### Follow-up Notebooks\n\nFor those looking to keep working on this problem, I have a series of follow-up notebooks:\n\n- [Manual Feature Engineering Part One](https://www.kaggle.com/willkoehrsen/introduction-to-manual-feature-engineering)\n- [Manual Feature Engineering Part Two](https://www.kaggle.com/willkoehrsen/introduction-to-manual-feature-engineering-p2)\n- [Introduction to Automated Feature Engineering](https://www.kaggle.com/willkoehrsen/automated-feature-engineering-basics)\n- [Advanced Automated Feature Engineering](https://www.kaggle.com/willkoehrsen/tuning-automated-feature-engineering-exploratory)\n- [Feature Selection](https://www.kaggle.com/willkoehrsen/introduction-to-feature-selection)\n- [Intro to Model Tuning: Grid and Random Search](https://www.kaggle.com/willkoehrsen/intro-to-model-tuning-grid-and-random-search//)","metadata":{}},{"cell_type":"markdown","source":"# Just for Fun: Light Gradient Boosting Machine\n\nNow (if you want, this part is entirely optional) we can step off the deep end and use a real machine learning model: the [gradient boosting machine](https://machinelearningmastery.com/gentle-introduction-gradient-boosting-algorithm-machine-learning/) using the [Light GBM library](http://lightgbm.readthedocs.io/en/latest/Quick-Start.html)! The Gradient Boosting Machine is currently the leading model for learning on structured datasets (especially on Kaggle) and we will probably need some form of this model to do well in the competition. Don't worry, even if this code looks intimidating, it's just a series of small steps that build up to a complete model. I added this code just to show what may be in store for this preject, and becaues it gets us a slightly better score on the leaderboard. In future notebooks we will see how to work with more advanced models (which mostly means adapting existing code to make it work better), feature engineering, and feature selection. See you in the next notebook!","metadata":{}},{"cell_type":"code","source":"    '''Train and test a light gradient boosting model using cross validation.\n    \n    Parameters\n    -----------\n        features (pd.DataFrame):\n            dataframe of training features to use\n            for training a model. Must include the TARGET column.\n        test_features (pd.DataFrame):\n            dataframe of testing features to use\n            for making predictions with the model.\n        encoding (str, default = 'ohe'):\n            method for encoding categorical variables.Either 'ohe' for one-hot encoding or 'le' for integer label encoding \n            n_folds (int, default = 5): number of folds to use for cross validation\n            \n    Return\n    -----------\n        submission (pd.DataFrame):\n            dataframe with 'SK_ID_CURR' and 'TARGET' probabilities\n            predicted by the model.\n        feature_importances (pd.DataFrame):\n            dataframe with the feature importances from the model.\n        valid_metrics (pd.DataFrame):\n            dataframe with training and validation metrics (ROC AUC) for each fold overall.\n    '''","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:39:36.722444Z","iopub.execute_input":"2022-07-26T04:39:36.722800Z","iopub.status.idle":"2022-07-26T04:39:36.731004Z","shell.execute_reply.started":"2022-07-26T04:39:36.722766Z","shell.execute_reply":"2022-07-26T04:39:36.730061Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import KFold\nfrom sklearn.metrics import roc_auc_score\nimport lightgbm as lgb\nimport gc\n\ndef model(features, test_features, encoding = 'ohe', n_folds = 5):\n    # Extract the ids\n    train_ids = features['SK_ID_CURR']\n    test_ids = test_features['SK_ID_CURR']\n    \n    # Extract the labels for training\n    labels = features['TARGET']\n    \n    # Remove the ids and target\n    features = features.drop(columns = ['SK_ID_CURR', 'TARGET'])\n    test_features = test_features.drop(columns = ['SK_ID_CURR'])\n    \n    \n    # One Hot Encoding\n    if encoding == 'ohe':\n        features = pd.get_dummies(features)\n        test_features = pd.get_dummies(test_features)\n        \n        # Align the dataframes by the columns\n        features, test_features = features.align(test_features, join = 'inner', axis = 1)\n        \n        # No categorical indices to record\n        cat_indices = 'auto'\n    \n    # Integer label encoding\n    elif encoding == 'le':\n        \n        # Create a label encoder\n        label_encoder = LabelEncoder()\n        \n        # List for storing categorical indices\n        cat_indices = []\n        \n        # Iterate through each column\n        for i, col in enumerate(features):\n            if features[col].dtype == 'object':\n                # Map the categorical features to integers\n                features[col] = label_encoder.fit_transform(np.array(features[col].astype(str)).reshape((-1,)))\n                test_features[col] = label_encoder.transform(np.array(test_features[col].astype(str)).reshape((-1,)))\n\n                # Record the categorical indices\n                cat_indices.append(i)\n    \n    # Catch error if label encoding scheme is not valid\n    else:\n        raise ValueError(\"Encoding must be either 'ohe' or 'le'\")\n        \n    print('Training Data Shape: ', features.shape)\n    print('Testing Data Shape: ', test_features.shape)\n    \n    # Extract feature names\n    feature_names = list(features.columns)\n    \n    # Convert to np arrays\n    features = np.array(features)\n    test_features = np.array(test_features)\n    \n    # Create the kfold object\n    k_fold = KFold(n_splits = n_folds, shuffle = True, random_state = 50)\n    \n    # Empty array for feature importances\n    feature_importance_values = np.zeros(len(feature_names))\n    \n    # Empty array for test predictions\n    test_predictions = np.zeros(test_features.shape[0])\n    \n    # Empty array for out of fold validation predictions\n    out_of_fold = np.zeros(features.shape[0])\n    \n    # Lists for recording validation and training scores\n    valid_scores = []\n    train_scores = []\n    \n    # Iterate through each fold\n    for train_indices, valid_indices in k_fold.split(features):\n        \n        # Training data for the fold\n        train_features, train_labels = features[train_indices], labels[train_indices]\n        # Validation data for the fold\n        valid_features, valid_labels = features[valid_indices], labels[valid_indices]\n        \n        # Create the model\n        model = lgb.LGBMClassifier(n_estimators=10000, objective = 'binary', \n                                   class_weight = 'balanced', learning_rate = 0.05, \n                                   reg_alpha = 0.1, reg_lambda = 0.1, \n                                   subsample = 0.8, n_jobs = -1, random_state = 50)\n        \n        # Train the model\n        model.fit(train_features, train_labels, eval_metric = 'auc',\n                  eval_set = [(valid_features, valid_labels), (train_features, train_labels)],\n                  eval_names = ['valid', 'train'], categorical_feature = cat_indices,\n                  early_stopping_rounds = 100, verbose = 200)\n        \n        # Record the best iteration\n        best_iteration = model.best_iteration_\n        \n        # Record the feature importances\n        feature_importance_values += model.feature_importances_ / k_fold.n_splits\n        \n        # Make predictions\n        test_predictions += model.predict_proba(test_features, num_iteration = best_iteration)[:, 1] / k_fold.n_splits\n        \n        # Record the out of fold predictions\n        out_of_fold[valid_indices] = model.predict_proba(valid_features, num_iteration = best_iteration)[:, 1]\n        \n        # Record the best score\n        valid_score = model.best_score_['valid']['auc']\n        train_score = model.best_score_['train']['auc']\n        \n        valid_scores.append(valid_score)\n        train_scores.append(train_score)\n        \n        # Clean up memory\n        gc.enable()\n        del model, train_features, valid_features\n        gc.collect()\n        \n    # Make the submission dataframe\n    submission = pd.DataFrame({'SK_ID_CURR': test_ids, 'TARGET': test_predictions})\n    \n    # Make the feature importance dataframe\n    feature_importances = pd.DataFrame({'feature': feature_names, 'importance': feature_importance_values})\n    \n    # Overall validation score\n    valid_auc = roc_auc_score(labels, out_of_fold)\n    \n    # Add the overall scores to the metrics\n    valid_scores.append(valid_auc)\n    train_scores.append(np.mean(train_scores))\n    \n    # Needed for creating dataframe of validation scores\n    fold_names = list(range(n_folds))\n    fold_names.append('overall')\n    \n    # Dataframe of validation scores\n    metrics = pd.DataFrame({'fold': fold_names,\n                            'train': train_scores,\n                            'valid': valid_scores}) \n    \n    return submission, feature_importances, metrics\n","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:54:16.899020Z","iopub.execute_input":"2022-07-26T04:54:16.899507Z","iopub.status.idle":"2022-07-26T04:54:16.929312Z","shell.execute_reply.started":"2022-07-26T04:54:16.899466Z","shell.execute_reply":"2022-07-26T04:54:16.927918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission, fi, metrics = model(app_train, app_test)\nprint('Baseline metrics')\nprint(metrics)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:54:18.503371Z","iopub.execute_input":"2022-07-26T04:54:18.504191Z","iopub.status.idle":"2022-07-26T04:58:28.087938Z","shell.execute_reply.started":"2022-07-26T04:54:18.504147Z","shell.execute_reply":"2022-07-26T04:58:28.086278Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fi_sorted = plot_feature_importances(fi)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:58:53.346512Z","iopub.execute_input":"2022-07-26T04:58:53.346965Z","iopub.status.idle":"2022-07-26T04:58:53.666101Z","shell.execute_reply.started":"2022-07-26T04:58:53.346928Z","shell.execute_reply":"2022-07-26T04:58:53.664827Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('baseline_lgb.csv', index = False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T04:58:55.177350Z","iopub.execute_input":"2022-07-26T04:58:55.178467Z","iopub.status.idle":"2022-07-26T04:58:55.357036Z","shell.execute_reply.started":"2022-07-26T04:58:55.178415Z","shell.execute_reply":"2022-07-26T04:58:55.355671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This submission should score about 0.735 on the leaderboard. We will certainly best that in future work!","metadata":{}},{"cell_type":"code","source":"app_train_domain['TARGET'] = train_labels\n\n# Test the domain knolwedge features\nsubmission_domain, fi_domain, metrics_domain = model(app_train_domain, app_test_domain)\nprint('Baseline with domain knowledge features metrics')\nprint(metrics_domain)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T05:00:22.289561Z","iopub.execute_input":"2022-07-26T05:00:22.290492Z","iopub.status.idle":"2022-07-26T05:04:32.965694Z","shell.execute_reply.started":"2022-07-26T05:00:22.290445Z","shell.execute_reply":"2022-07-26T05:04:32.964529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fi_sorted = plot_feature_importances(fi_domain)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T05:48:49.576149Z","iopub.execute_input":"2022-07-26T05:48:49.577357Z","iopub.status.idle":"2022-07-26T05:48:49.871376Z","shell.execute_reply.started":"2022-07-26T05:48:49.577275Z","shell.execute_reply":"2022-07-26T05:48:49.869979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Again, we see the some of our features made it into the most important. Going forward, we will need to think about whatother domain knowledge features may be useful for this problem(or we should consult someone who knows more about the financial industry!","metadata":{}},{"cell_type":"code","source":"submission_domain.to_csv('baseline_lgb_domain_features.csv', index = False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T05:50:54.518688Z","iopub.execute_input":"2022-07-26T05:50:54.519253Z","iopub.status.idle":"2022-07-26T05:50:54.703972Z","shell.execute_reply.started":"2022-07-26T05:50:54.519205Z","shell.execute_reply":"2022-07-26T05:50:54.702473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This model scroes about 0.754 when submitted to the public leaderboard indicating that the domain features do imporve the performance! Feature Engineering is going to be a critical part of this competition (as it is for all machine learning problems)!","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}