{"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":"**This notebook is an exercise in the [Intermediate Machine Learning](https://www.kaggle.com/learn/intermediate-machine-learning) course.  You can reference the tutorial at [this link](https://www.kaggle.com/alexisbcook/missing-values).**\n\n---\n","metadata":{}},{"cell_type":"markdown","source":"Now it's your turn to test your new knowledge of **missing values** handling. You'll probably find it makes a big difference.\n\n# Setup\n\nThe questions will give you feedback on your work. Run the following cell to set up the feedback system.","metadata":{}},{"cell_type":"code","source":"# Set up code checking\nimport os\nif not os.path.exists(\"../input/train.csv\"):\n    os.symlink(\"../input/home-data-for-ml-course/train.csv\", \"../input/train.csv\")  \n    os.symlink(\"../input/home-data-for-ml-course/test.csv\", \"../input/test.csv\") \nfrom learntools.core import binder\nbinder.bind(globals())\nfrom learntools.ml_intermediate.ex2 import *\nprint(\"Setup Complete\")","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.524896Z","iopub.execute_input":"2022-07-05T10:29:40.525303Z","iopub.status.idle":"2022-07-05T10:29:40.534651Z","shell.execute_reply.started":"2022-07-05T10:29:40.525258Z","shell.execute_reply":"2022-07-05T10:29:40.533654Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In this exercise, you will work with data from the [Housing Prices Competition for Kaggle Learn Users](https://www.kaggle.com/c/home-data-for-ml-course). \n\n![Ames Housing dataset image](https://i.imgur.com/lTJVG4e.png)\n\nRun the next code cell without changes to load the training and validation sets in `X_train`, `X_valid`, `y_train`, and `y_valid`.  The test set is loaded in `X_test`.","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nfrom sklearn.model_selection import train_test_split\n\n# Read the data\nX_full = pd.read_csv('../input/train.csv', index_col='Id')\nX_test_full = pd.read_csv('../input/test.csv', index_col='Id')\n\n# Remove rows with missing target, separate target from predictors\nX_full.dropna(axis=0, subset=['SalePrice'], inplace=True)\ny = X_full.SalePrice\nX_full.drop(['SalePrice'], axis=1, inplace=True)\n\n# To keep things simple, we'll use only numerical predictors\nX = X_full.select_dtypes(exclude=['object'])\nX_test = X_test_full.select_dtypes(exclude=['object'])\n\n# Break off validation set from training data\nX_train, X_valid, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2,\n                                                      random_state=0)","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.539017Z","iopub.execute_input":"2022-07-05T10:29:40.539377Z","iopub.status.idle":"2022-07-05T10:29:40.621792Z","shell.execute_reply.started":"2022-07-05T10:29:40.539343Z","shell.execute_reply":"2022-07-05T10:29:40.620703Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Use the next code cell to print the first five rows of the data.","metadata":{}},{"cell_type":"code","source":"X_train.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.624623Z","iopub.execute_input":"2022-07-05T10:29:40.625073Z","iopub.status.idle":"2022-07-05T10:29:40.649262Z","shell.execute_reply.started":"2022-07-05T10:29:40.625026Z","shell.execute_reply":"2022-07-05T10:29:40.648083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"You can already see a few missing values in the first several rows.  In the next step, you'll obtain a more comprehensive understanding of the missing values in the dataset.\n\n# Step 1: Preliminary investigation\n\nRun the code cell below without changes.","metadata":{}},{"cell_type":"code","source":"# Shape of training data (num_rows, num_columns)\nprint(X_train.shape)\n\n# Number of missing values in each column of training data\nmissing_val_count_by_column = (X_train.isnull().sum())\nprint(missing_val_count_by_column[missing_val_count_by_column > 0])","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.651084Z","iopub.execute_input":"2022-07-05T10:29:40.651811Z","iopub.status.idle":"2022-07-05T10:29:40.665673Z","shell.execute_reply.started":"2022-07-05T10:29:40.651766Z","shell.execute_reply":"2022-07-05T10:29:40.664382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Part A\n\nUse the above output to answer the questions below.","metadata":{}},{"cell_type":"code","source":"# Fill in the line below: How many rows are in the training data?\nnum_rows = 1168\n\n# Fill in the line below: How many columns in the training data\n# have missing values?\nnum_cols_with_missing = 3\n\n# Fill in the line below: How many missing entries are contained in \n# all of the training data?\ntot_missing = 276\n\n# Check your answers\nstep_1.a.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.669447Z","iopub.execute_input":"2022-07-05T10:29:40.670041Z","iopub.status.idle":"2022-07-05T10:29:40.679985Z","shell.execute_reply.started":"2022-07-05T10:29:40.670007Z","shell.execute_reply":"2022-07-05T10:29:40.678723Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Lines below will give you a hint or solution code\n#step_1.a.hint()\n#step_1.a.solution()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.681672Z","iopub.execute_input":"2022-07-05T10:29:40.682204Z","iopub.status.idle":"2022-07-05T10:29:40.691739Z","shell.execute_reply.started":"2022-07-05T10:29:40.682164Z","shell.execute_reply":"2022-07-05T10:29:40.690352Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Part B\nConsidering your answers above, what do you think is likely the best approach to dealing with the missing values?","metadata":{}},{"cell_type":"code","source":"# Check your answer (Run this code cell to receive credit!)\nstep_1.b.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.692993Z","iopub.execute_input":"2022-07-05T10:29:40.693511Z","iopub.status.idle":"2022-07-05T10:29:40.708263Z","shell.execute_reply.started":"2022-07-05T10:29:40.693479Z","shell.execute_reply":"2022-07-05T10:29:40.707361Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#step_1.b.hint()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.709753Z","iopub.execute_input":"2022-07-05T10:29:40.710098Z","iopub.status.idle":"2022-07-05T10:29:40.717125Z","shell.execute_reply.started":"2022-07-05T10:29:40.710066Z","shell.execute_reply":"2022-07-05T10:29:40.715561Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"To compare different approaches to dealing with missing values, you'll use the same `score_dataset()` function from the tutorial.  This function reports the [mean absolute error](https://en.wikipedia.org/wiki/Mean_absolute_error) (MAE) from a random forest model.","metadata":{}},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestRegressor\nfrom sklearn.metrics import mean_absolute_error\n\n# Function for comparing different approaches\ndef score_dataset(X_train, X_valid, y_train, y_valid):\n    model = RandomForestRegressor(n_estimators=100, random_state=0)\n    model.fit(X_train, y_train)\n    preds = model.predict(X_valid)\n    return mean_absolute_error(y_valid, preds)","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.719173Z","iopub.execute_input":"2022-07-05T10:29:40.720784Z","iopub.status.idle":"2022-07-05T10:29:40.729732Z","shell.execute_reply.started":"2022-07-05T10:29:40.720743Z","shell.execute_reply":"2022-07-05T10:29:40.728563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 2: Drop columns with missing values\n\nIn this step, you'll preprocess the data in `X_train` and `X_valid` to remove columns with missing values.  Set the preprocessed DataFrames to `reduced_X_train` and `reduced_X_valid`, respectively.  ","metadata":{}},{"cell_type":"code","source":"# Fill in the line below: get names of columns with missing values\ncols_with_missing = [col for col in X_train.columns\n                     if X_train[col].isnull().any()] # Your code here\n\n# Fill in the lines below: drop columns in training and validation data\nreduced_X_train = X_train.drop(cols_with_missing, axis=1)\nreduced_X_valid = X_valid.drop(cols_with_missing, axis=1)\n\n# Check your answers\nstep_2.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.731472Z","iopub.execute_input":"2022-07-05T10:29:40.732306Z","iopub.status.idle":"2022-07-05T10:29:40.771989Z","shell.execute_reply.started":"2022-07-05T10:29:40.732233Z","shell.execute_reply":"2022-07-05T10:29:40.770671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Lines below will give you a hint or solution code\n#step_2.hint()\n#step_2.solution()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.775720Z","iopub.execute_input":"2022-07-05T10:29:40.776177Z","iopub.status.idle":"2022-07-05T10:29:40.780576Z","shell.execute_reply.started":"2022-07-05T10:29:40.776142Z","shell.execute_reply":"2022-07-05T10:29:40.779669Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Run the next code cell without changes to obtain the MAE for this approach.","metadata":{}},{"cell_type":"code","source":"print(\"MAE (Drop columns with missing values):\")\nprint(score_dataset(reduced_X_train, reduced_X_valid, y_train, y_valid))","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:40.782108Z","iopub.execute_input":"2022-07-05T10:29:40.782720Z","iopub.status.idle":"2022-07-05T10:29:41.933260Z","shell.execute_reply.started":"2022-07-05T10:29:40.782684Z","shell.execute_reply":"2022-07-05T10:29:41.932069Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 3: Imputation\n\n### Part A\n\nUse the next code cell to impute missing values with the mean value along each column.  Set the preprocessed DataFrames to `imputed_X_train` and `imputed_X_valid`.  Make sure that the column names match those in `X_train` and `X_valid`.","metadata":{}},{"cell_type":"code","source":"from sklearn.impute import SimpleImputer\n\n# Fill in the lines below: imputation\nmy_imputer = SimpleImputer()\nimputed_X_train = pd.DataFrame(my_imputer.fit_transform(X_train))\nimputed_X_valid = pd.DataFrame(my_imputer.transform(X_valid))\n\n# Imputation removed column names; put them back\nimputed_X_train.columns = X_train.columns\nimputed_X_valid.columns = X_valid.columns\n\n# Check your answers\nstep_3.a.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:41.934900Z","iopub.execute_input":"2022-07-05T10:29:41.935387Z","iopub.status.idle":"2022-07-05T10:29:41.970339Z","shell.execute_reply.started":"2022-07-05T10:29:41.935340Z","shell.execute_reply":"2022-07-05T10:29:41.969170Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Lines below will give you a hint or solution code\n#step_3.a.hint()\nstep_3.a.solution()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:41.971591Z","iopub.execute_input":"2022-07-05T10:29:41.971995Z","iopub.status.idle":"2022-07-05T10:29:41.980301Z","shell.execute_reply.started":"2022-07-05T10:29:41.971963Z","shell.execute_reply":"2022-07-05T10:29:41.979364Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Run the next code cell without changes to obtain the MAE for this approach.","metadata":{}},{"cell_type":"code","source":"print(\"MAE (Imputation):\")\nprint(score_dataset(imputed_X_train, imputed_X_valid, y_train, y_valid))","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:41.981800Z","iopub.execute_input":"2022-07-05T10:29:41.982558Z","iopub.status.idle":"2022-07-05T10:29:43.242855Z","shell.execute_reply.started":"2022-07-05T10:29:41.982525Z","shell.execute_reply":"2022-07-05T10:29:43.240655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Part B\n\nCompare the MAE from each approach.  Does anything surprise you about the results?  Why do you think one approach performed better than the other?","metadata":{}},{"cell_type":"code","source":"# Check your answer (Run this code cell to receive credit!)\nstep_3.b.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:43.245176Z","iopub.execute_input":"2022-07-05T10:29:43.245671Z","iopub.status.idle":"2022-07-05T10:29:43.263706Z","shell.execute_reply.started":"2022-07-05T10:29:43.245622Z","shell.execute_reply":"2022-07-05T10:29:43.261152Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#step_3.b.hint()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:43.265905Z","iopub.execute_input":"2022-07-05T10:29:43.266709Z","iopub.status.idle":"2022-07-05T10:29:43.273418Z","shell.execute_reply.started":"2022-07-05T10:29:43.266654Z","shell.execute_reply":"2022-07-05T10:29:43.271341Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 4: Generate test predictions\n\nIn this final step, you'll use any approach of your choosing to deal with missing values.  Once you've preprocessed the training and validation features, you'll train and evaluate a random forest model.  Then, you'll preprocess the test data before generating predictions that can be submitted to the competition!\n\n### Part A\n\nUse the next code cell to preprocess the training and validation data.  Set the preprocessed DataFrames to `final_X_train` and `final_X_valid`.  **You can use any approach of your choosing here!**  in order for this step to be marked as correct, you need only ensure:\n- the preprocessed DataFrames have the same number of columns,\n- the preprocessed DataFrames have no missing values, \n- `final_X_train` and `y_train` have the same number of rows, and\n- `final_X_valid` and `y_valid` have the same number of rows.","metadata":{}},{"cell_type":"code","source":"# Preprocessed training and validation features\nfinal_imputer = SimpleImputer(strategy='median')\nfinal_X_train = pd.DataFrame(final_imputer.fit_transform(X_train))\nfinal_X_valid = pd.DataFrame(final_imputer.transform(X_valid))\n\n# Imputation removed column names; put them back\nfinal_X_train.columns = X_train.columns\nfinal_X_valid.columns = X_valid.columns\n\n# Check your answers\nstep_4.a.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:30:34.810972Z","iopub.execute_input":"2022-07-05T10:30:34.811729Z","iopub.status.idle":"2022-07-05T10:30:34.850060Z","shell.execute_reply.started":"2022-07-05T10:30:34.811670Z","shell.execute_reply":"2022-07-05T10:30:34.849158Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Lines below will give you a hint or solution code\n#step_4.a.hint()\nstep_4.a.solution()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:29:43.292646Z","iopub.execute_input":"2022-07-05T10:29:43.293763Z","iopub.status.idle":"2022-07-05T10:29:43.310934Z","shell.execute_reply.started":"2022-07-05T10:29:43.293707Z","shell.execute_reply":"2022-07-05T10:29:43.308088Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Run the next code cell to train and evaluate a random forest model.  (*Note that we don't use the `score_dataset()` function above, because we will soon use the trained model to generate test predictions!*)","metadata":{}},{"cell_type":"code","source":"# Define and fit model\nmodel = RandomForestRegressor(n_estimators=100, random_state=0)\nmodel.fit(final_X_train, y_train)\n\n# Get validation predictions and MAE\npreds_valid = model.predict(final_X_valid)\nprint(\"MAE (Your approach):\")\nprint(mean_absolute_error(y_valid, preds_valid))","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:30:43.935014Z","iopub.execute_input":"2022-07-05T10:30:43.935418Z","iopub.status.idle":"2022-07-05T10:30:45.187065Z","shell.execute_reply.started":"2022-07-05T10:30:43.935384Z","shell.execute_reply":"2022-07-05T10:30:45.185674Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Part B\n\nUse the next code cell to preprocess your test data.  Make sure that you use a method that agrees with how you preprocessed the training and validation data, and set the preprocessed test features to `final_X_test`.\n\nThen, use the preprocessed test features and the trained model to generate test predictions in `preds_test`.\n\nIn order for this step to be marked correct, you need only ensure:\n- the preprocessed test DataFrame has no missing values, and\n- `final_X_test` has the same number of rows as `X_test`.","metadata":{}},{"cell_type":"code","source":"# Preprocess test data\nfinal_X_test = pd.DataFrame(final_imputer.transform(X_test))\n\n# Get test predictions\npreds_test = model.predict(final_X_test)\n# Check your answers\nstep_4.b.check()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:33:09.547738Z","iopub.execute_input":"2022-07-05T10:33:09.549241Z","iopub.status.idle":"2022-07-05T10:33:09.609834Z","shell.execute_reply.started":"2022-07-05T10:33:09.549188Z","shell.execute_reply":"2022-07-05T10:33:09.608354Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Lines below will give you a hint or solution code\n#step_4.b.hint()\n\nstep_4.b.solution()","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:31:05.085264Z","iopub.execute_input":"2022-07-05T10:31:05.085713Z","iopub.status.idle":"2022-07-05T10:31:05.095068Z","shell.execute_reply.started":"2022-07-05T10:31:05.085631Z","shell.execute_reply":"2022-07-05T10:31:05.094207Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Run the next code cell without changes to save your results to a CSV file that can be submitted directly to the competition.","metadata":{}},{"cell_type":"code","source":"# Save test predictions to file\noutput = pd.DataFrame({'Id': X_test.index,\n                       'SalePrice': preds_test})\noutput.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-07-05T10:33:28.800667Z","iopub.execute_input":"2022-07-05T10:33:28.803213Z","iopub.status.idle":"2022-07-05T10:33:28.815760Z","shell.execute_reply.started":"2022-07-05T10:33:28.803171Z","shell.execute_reply":"2022-07-05T10:33:28.814749Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submit your results\n\nOnce you have successfully completed Step 4, you're ready to submit your results to the leaderboard!  (_You also learned how to do this in the previous exercise.  If you need a reminder of how to do this, please use the instructions below._)  \n\nFirst, you'll need to join the competition if you haven't already.  So open a new window by clicking on [this link](https://www.kaggle.com/c/home-data-for-ml-course).  Then click on the **Join Competition** button.\n\n![join competition image](https://i.imgur.com/wLmFtH3.png)\n\nNext, follow the instructions below:\n1. Begin by clicking on the **Save Version** button in the top right corner of the window.  This will generate a pop-up window.  \n2. Ensure that the **Save and Run All** option is selected, and then click on the **Save** button.\n3. This generates a window in the bottom left corner of the notebook.  After it has finished running, click on the number to the right of the **Save Version** button.  This pulls up a list of versions on the right of the screen.  Click on the ellipsis **(...)** to the right of the most recent version, and select **Open in Viewer**.  This brings you into view mode of the same page. You will need to scroll down to get back to these instructions.\n4. Click on the **Output** tab on the right of the screen.  Then, click on the file you would like to submit, and click on the **Submit** button to submit your results to the leaderboard.\n\nYou have now successfully submitted to the competition!\n\nIf you want to keep working to improve your performance, select the **Edit** button in the top right of the screen. Then you can change your code and repeat the process. There's a lot of room to improve, and you will climb up the leaderboard as you work.\n\n\n# Keep going\n\nMove on to learn what **[categorical variables](https://www.kaggle.com/alexisbcook/categorical-variables)** are, along with how to incorporate them into your machine learning models.  Categorical variables are very common in real-world data, but you'll get an error if you try to plug them into your models without processing them first!","metadata":{}},{"cell_type":"markdown","source":"---\n\n\n\n\n*Have questions or comments? Visit the [course discussion forum](https://www.kaggle.com/learn/intermediate-machine-learning/discussion) to chat with other learners.*","metadata":{}}]}