{"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":"<div style=\"padding:30px;color:white;margin:0;font-size:280%;text-align:center;display:fill;border-radius:5px;background-color:#11202e;overflow:hidden;font-weight:500\">➡️ Tutorial ✅ 07 Cross Validation Methods 📊</div>","metadata":{}},{"cell_type":"markdown","source":"**Cross-validation is a statistical method used to estimate the performance of machine learning models. It is a method for assessing how the results of a statistical analysis will generalize to an independent data set.**\nCross-validation is a technique for evaluating ML models by training several ML models on subsets of the available input data and evaluating them on the complementary subset of the data. Use cross-validation to detect overfitting, failing to generalize a pattern.","metadata":{}},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:200%;text-align:center;display:fill;border-radius:5px;background-color:#4287f5;overflow:hidden;font-weight:500\">How does it tackle the problem of overfitting?</div>\n<p></br></p>\n\nIn Cross-Validation, we use our initial training data to generate multiple mini train-test splits. Use these splits to tune your model. For example in standard k-fold cross-validation, we partition the data into k subsets. Then, we iteratively train the algorithm on k-1 subsets while using the remaining subset as the test set. In this way, we can test our model on completely unseen data. In this article, you can read about the 7 most commonly used cross-validation techniques along with their pros and cons. I have also provided the code snippets for each technique.","metadata":{}},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#255cb3;overflow:hidden;font-weight:500\">The techniques</div>\n<p></br></p>\n# The techniques are listed below:\n- Hold Out Cross-validation\n- K-Fold cross-validation\n- Stratified K-Fold cross-validation\n- Leave Pout Cross-validation\n- Leave One Out Cross-validation\n- Monte Carlo (Shuffle-Split)\n- Time Series ( Rolling cross-validation)","metadata":{}},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:200%;text-align:center;display:fill;border-radius:5px;background-color:#255cb3;overflow:hidden;font-weight:500\">What are the steps of cross-validation?</div> </br>\n\n1. Divide data set at random into training and test sets.\n2. Fit model on training set.\n3. Test model on test set.\n4. Compute and save fit statistic using test data (step 3).\n5. Repeat 1 - 4 several times, then average results of all step 4.","metadata":{}},{"cell_type":"markdown","source":"## Creating Random Samples","metadata":{"_kg_hide-input":true,"_kg_hide-output":true}},{"cell_type":"code","source":"import random\nli=random.sample(range(10, 130), 24)","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:00.561715Z","iopub.execute_input":"2022-05-05T08:14:00.562019Z","iopub.status.idle":"2022-05-05T08:14:00.566038Z","shell.execute_reply.started":"2022-05-05T08:14:00.561983Z","shell.execute_reply":"2022-05-05T08:14:00.565318Z"},"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">HoldOut Cross-validation or Train-Test Split</div>","metadata":{}},{"cell_type":"markdown","source":"# 1. HoldOut Cross-validation or Train-Test Split\n\nIn this technique of cross-validation, the whole dataset is randomly partitioned into a training set and validation set. Using a rule of thumb nearly 70% of the whole dataset is used as a training set and the remaining 30% is used as the validation set.\n\n<p></br></p>\n\n![HoldOut Cross-validation or Train-Test Split.png](attachment:7a80ffc7-954d-461c-a28a-c8b986404736.png)\n\n<p></br></p>\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#1a8236;overflow:hidden;font-weight:500\"> #   Pros</div><p></br></p>\n\n**1. Quick To Execute:**\nAs we have to split the dataset into training and validation set just once and the model will be built just once on the training set so gets executed quickly.\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#f00707;overflow:hidden;font-weight:500\"> #   Cons</div><p></br></p>\n\n**1. Not Suitable for an imbalanced dataset:**\nSuppose we have an imbalanced dataset that has class ‘0’ and class ‘1’. Let’s say 80% of data belongs to class ‘0’ and the remaining 20% data to class ‘1’.On doing train-test split with train set size as 80% and test data size as 20% of the dataset. It may happen that all 80% data of class ‘0’ may be in the training set and all data of class ‘1’ in the test set. So our model will not generalize well for our test data as it hasn’t seen data of class ‘1’ before.\n\n**2. A large chunk of data gets deprived of training the model.**\nIn the case of a small dataset, a part will be kept aside for testing the model which may have important characteristics which our model may miss out on as it has not trained on that data.\n\n</br><div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>\n","metadata":{},"attachments":{"7a80ffc7-954d-461c-a28a-c8b986404736.png":{"image/png":"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"}}},{"cell_type":"code","source":"from sklearn.datasets import load_iris\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import accuracy_score\n\niris=load_iris()\nX=iris.data[li]\nY=iris.target[li]\nprint(\"Size of Dataset {}\".format(len(X)))\n\n\nlogreg=LogisticRegression()\n\nx_train,x_test,y_train,y_test=train_test_split(X,Y,test_size=0.3,random_state=42)\nlogreg.fit(x_train,y_train)\npredict=logreg.predict(x_test)","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:00.676951Z","iopub.execute_input":"2022-05-05T08:14:00.677453Z","iopub.status.idle":"2022-05-05T08:14:00.703385Z","shell.execute_reply.started":"2022-05-05T08:14:00.677421Z","shell.execute_reply":"2022-05-05T08:14:00.702544Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Accuracy score on training set is {}\".format(accuracy_score(logreg.predict(x_train),y_train)))\nprint(\"Accuracy score on test set is {}\".format(accuracy_score(predict,y_test)))","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:00.788482Z","iopub.execute_input":"2022-05-05T08:14:00.78874Z","iopub.status.idle":"2022-05-05T08:14:00.795599Z","shell.execute_reply.started":"2022-05-05T08:14:00.788712Z","shell.execute_reply":"2022-05-05T08:14:00.795031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">K-Fold Cross-Validation</div>","metadata":{}},{"cell_type":"markdown","source":"# 2. K-Fold Cross-Validation\n\nIn this technique of K-Fold cross-validation, the whole dataset is partitioned into K parts of equal size. Each partition is called a “Fold“.So as we have K parts we call it K-Folds. One Fold is used as a validation set and the remaining K-1 folds are used as the training set.\n\nThe technique is repeated K times until each fold is used as a validation set and the remaining folds as the training set.\n\nThe final accuracy of the model is computed by taking the mean accuracy of the k-models validation data.\n\n\n\n\n\n\n![kfold.png](attachment:2567948b-3353-4ba4-aa2f-273372605167.png)\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#1a8236;overflow:hidden;font-weight:500\"> #   Pros</div><p></br></p>\n\n1. **The whole dataset is used as both a training set and validation set**\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#f00707;overflow:hidden;font-weight:500\"> #   Cons</div><p></br></p>\n\n1. **Not to be used for imbalanced datasets**: \nAs discussed in the case of HoldOut cross-validation, in the case of K-Fold validation too it may happen that all samples of training set will have no sample form class “1” and only of class “0”.And the validation set will have a sample of class “1”.\n\n2. **Not suitable for Time Series data**: \nFor Time Series data the order of the samples matter. But in K-Fold Cross-Validation, samples are selected in random order.\n\n\n</br><div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>","metadata":{},"attachments":{"2567948b-3353-4ba4-aa2f-273372605167.png":{"image/png":"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"}}},{"cell_type":"code","source":"from sklearn.datasets import load_iris\nfrom sklearn.model_selection import cross_val_score,KFold\nfrom sklearn.linear_model import LogisticRegression\n\niris=load_iris()\n\nX=iris.data[li]\nY=iris.target[li]\n\nlogreg=LogisticRegression()\nkf=KFold(n_splits=5)\nscore=cross_val_score(logreg,X,Y,cv=kf)\n","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-05-05T08:14:42.934674Z","iopub.execute_input":"2022-05-05T08:14:42.935023Z","iopub.status.idle":"2022-05-05T08:14:43.031336Z","shell.execute_reply.started":"2022-05-05T08:14:42.934961Z","shell.execute_reply":"2022-05-05T08:14:43.030365Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Cross Validation Scores are {}\".format(score))\nprint(\"Average Cross Validation score :{}\".format(score.mean()))","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:00.931816Z","iopub.execute_input":"2022-05-05T08:14:00.932265Z","iopub.status.idle":"2022-05-05T08:14:00.938784Z","shell.execute_reply.started":"2022-05-05T08:14:00.932217Z","shell.execute_reply":"2022-05-05T08:14:00.937999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">Stratified K-Fold Cross-Validation</div>","metadata":{}},{"cell_type":"markdown","source":"# 3. Stratified K-Fold Cross-Validation\n\nStratified K-Fold is an enhanced version of K-Fold cross-validation which is mainly used for imbalanced datasets. Just like K-fold, the whole dataset is divided into K-folds of equal size.\n\nBut in this technique, each fold will have the same ratio of instances of target variable as in the whole datasets\n<p></br></p>\n\n![3. Stratified K-Fold Cross-Validation.png](attachment:50411830-309e-45db-baeb-50326e99d8ff.png)\n\n<p></br></p>\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#1a8236;overflow:hidden;font-weight:500\"> #   Pros</div><p></br></p>\n\n1. Works perfectly well for Imbalanced Data: Each fold in stratified cross-validation will have a representation of data of all classes in the same ratio as in the whole dataset.\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#f00707;overflow:hidden;font-weight:500\"> #   Cons</div><p></br></p>\n\n1. **Not suitable for Time Series data**: For Time Series data the order of the samples matter. But in Stratified Cross-Validation, samples are selected in random order.\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>","metadata":{},"attachments":{"50411830-309e-45db-baeb-50326e99d8ff.png":{"image/png":"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"}}},{"cell_type":"code","source":"from sklearn.model_selection import cross_val_score,StratifiedKFold\nfrom sklearn.linear_model import LogisticRegression\n\niris=load_iris()\nX=iris.data[li]\nY=iris.target[li]\n\nlogreg=LogisticRegression()\nstratifiedkf=StratifiedKFold(n_splits=5)\n\nscore=cross_val_score(logreg,X,Y,cv=stratifiedkf)\n","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-05-05T08:14:00.967586Z","iopub.execute_input":"2022-05-05T08:14:00.967887Z","iopub.status.idle":"2022-05-05T08:14:01.053963Z","shell.execute_reply.started":"2022-05-05T08:14:00.967852Z","shell.execute_reply":"2022-05-05T08:14:01.053047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Cross Validation Scores are {}\".format(score))\nprint(\"Average Cross Validation score :{}\".format(score.mean()))","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:01.055487Z","iopub.execute_input":"2022-05-05T08:14:01.055725Z","iopub.status.idle":"2022-05-05T08:14:01.061808Z","shell.execute_reply.started":"2022-05-05T08:14:01.055696Z","shell.execute_reply":"2022-05-05T08:14:01.060938Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">Leave P Out cross-validation</div>","metadata":{}},{"cell_type":"markdown","source":"# 4. Leave P Out cross-validation\n\n\nLeavePOut cross-validation is an exhaustive cross-validation technique, in which p-samples are used as the validation set and remaining n-p samples are used as the training set.\n\nSuppose we have 100 samples in the dataset. If we use p=10 then in each iteration 10 values will be used as a validation set and the remaining 90 samples as the training set.\n\nThis process is repeated till the whole dataset gets divided on the validation set of p-samples and n-p training samples.\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#1a8236;overflow:hidden;font-weight:500\"> #   Pros</div><p></br></p>\n\nAll the data samples get used as both training and validation samples.\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#f00707;overflow:hidden;font-weight:500\"> #   Cons</div><p></br></p>\n\n1. **High computation time**: As the above technique will keep on repeating until all samples get used up as a validation set, it will have higher computational time.\n\n2. **Not Suitable for Imbalanced dataset**: Same as in K-Fold Cross-validation, if in the training set we have samples of only 1 class then our model will not be able to generalize for the validation set.\n\n</br><div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>","metadata":{}},{"cell_type":"code","source":"from sklearn.model_selection import LeavePOut,cross_val_score\nfrom sklearn.datasets import load_iris\nfrom sklearn.ensemble import RandomForestClassifier\n\niris=load_iris()\nX=iris.data[li]\nY=iris.target[li]\n\nlpo=LeavePOut(p=2)\nlpo.get_n_splits(X)\n\ntree=RandomForestClassifier(n_estimators=10,max_depth=5,n_jobs=-1)\n\nscore=cross_val_score(tree,X,Y,cv=lpo)","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-05-05T08:14:01.092613Z","iopub.execute_input":"2022-05-05T08:14:01.09292Z","iopub.status.idle":"2022-05-05T08:14:39.408642Z","shell.execute_reply.started":"2022-05-05T08:14:01.092886Z","shell.execute_reply":"2022-05-05T08:14:39.407326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Cross Validation Scores are \\n{}\".format(score))\nprint(\"Average Cross Validation score :{}\".format(score.mean()))","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:39.411938Z","iopub.execute_input":"2022-05-05T08:14:39.412484Z","iopub.status.idle":"2022-05-05T08:14:39.421823Z","shell.execute_reply.started":"2022-05-05T08:14:39.412438Z","shell.execute_reply":"2022-05-05T08:14:39.420989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">Leave One Out cross-validation</div>","metadata":{}},{"cell_type":"markdown","source":"# 5. Leave One Out cross-validation\n\nLeaveOneOut cross-validation is an exhaustive cross-validation technique in which 1 sample point is used as a validation set and the remaining n-1 samples are used as the training set.\n\nSuppose we have 100 samples in the dataset. Then in each iteration 1 value will be used as a validation set and the remaining 99 samples as the training set. Thus the process is repeated till every sample of the dataset is used as a validation point.\n\nIt is the same as LeavePOut cross-validation with p=1.\n\n\n\n![5. Leave One Out cross-validation.gif](attachment:4b06000d-c5b9-40c5-88af-bbf77db64014.gif)\n\n</br><div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>","metadata":{},"attachments":{"4b06000d-c5b9-40c5-88af-bbf77db64014.gif":{"image/gif":"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"}}},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\nfrom sklearn.model_selection import LeaveOneOut,cross_val_score\n\niris=load_iris()\nX=iris.data[li]\nY=iris.target[li]\n\nloo=LeaveOneOut()\ntree=RandomForestClassifier(n_estimators=10,max_depth=5,n_jobs=-1)\nscore=cross_val_score(tree,X,Y,cv=loo)","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-05-05T08:14:39.422935Z","iopub.execute_input":"2022-05-05T08:14:39.4232Z","iopub.status.idle":"2022-05-05T08:14:42.722355Z","shell.execute_reply.started":"2022-05-05T08:14:39.423162Z","shell.execute_reply":"2022-05-05T08:14:42.721272Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Cross Validation Scores are {}\".format(score))\nprint(\"Average Cross Validation score :{}\".format(score.mean()))","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:42.725054Z","iopub.execute_input":"2022-05-05T08:14:42.72564Z","iopub.status.idle":"2022-05-05T08:14:42.732645Z","shell.execute_reply.started":"2022-05-05T08:14:42.725593Z","shell.execute_reply":"2022-05-05T08:14:42.731901Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">Monte Carlo Cross-Validation(Shuffle Split)</div>","metadata":{}},{"cell_type":"markdown","source":"# 6. Monte Carlo Cross-Validation(Shuffle Split)\n\n\nMonte Carlo cross-validation, also known as Shuffle Split cross-validation, is a very flexible strategy of cross-validation. In this technique, the datasets get randomly partitioned into training and validation sets.\n\nWe have decided upon the percentage of the dataset we want to be used as a training set and the percentage to be used as a validation set. If the added percentage of training and validation set size is not sum up to 100 then the remaining dataset is not used in either training or validation set.\n\nLet’s say we have 100 samples and 60% of samples to be used as training set and 20% of the sample to be used as validation set then the remaining 20%( 100-(60+20)) is not to be used.\n\nThis splitting will be repeated ‘n’ times that we have to specify.\n\n![monte carlo.png](attachment:87fd491f-2eef-4ca7-ae9b-036b2bfdc0bc.png)","metadata":{},"attachments":{"87fd491f-2eef-4ca7-ae9b-036b2bfdc0bc.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#1a8236;overflow:hidden;font-weight:500\"> #   Pros</div><p></br></p>\n\n1. We are free to use the size of the training and validation set.\n\n2. We can choose the number of repetitions and not depend on the number of folds for repetitions.\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#f00707;overflow:hidden;font-weight:500\"> #   Cons</div><p></br></p>\n\n1. Few samples may not be selected for either training or validation set.\n\n2. Not Suitable for Imbalanced datasets: After we define the size of the training set and validation set, all the samples are randomly selected, so it may happen that the training set may don’t have the class of data that is in the test set, and the model won’t be able to generalize for unseen data.\n\n\n</br><div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>","metadata":{}},{"cell_type":"code","source":"from sklearn.model_selection import ShuffleSplit,cross_val_score\nfrom sklearn.linear_model import LogisticRegression\n\nlogreg=LogisticRegression()\n\nshuffle_split=ShuffleSplit(test_size=0.3,train_size=0.5,n_splits=10)\n\nscores=cross_val_score(logreg,iris.data[li],iris.target[li],cv=shuffle_split)","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-05-05T08:14:42.734493Z","iopub.execute_input":"2022-05-05T08:14:42.735188Z","iopub.status.idle":"2022-05-05T08:14:42.905516Z","shell.execute_reply.started":"2022-05-05T08:14:42.735004Z","shell.execute_reply":"2022-05-05T08:14:42.9047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"cross Validation scores:n {}\".format(scores))\nprint(\"Average Cross Validation score :{}\".format(scores.mean()))","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:42.906635Z","iopub.execute_input":"2022-05-05T08:14:42.90685Z","iopub.status.idle":"2022-05-05T08:14:42.912916Z","shell.execute_reply.started":"2022-05-05T08:14:42.906813Z","shell.execute_reply":"2022-05-05T08:14:42.9118Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#f7055e;overflow:hidden;font-weight:500\">Time Series Cross-Validation</div>","metadata":{}},{"cell_type":"markdown","source":"# 7. Time Series Cross-Validation\n\n## What is a Time Series Data?\n\nTime series data is data that is collected at different points in time. As the data points are collected at adjacent time periods there is potential for correlation between observations. This is one of the features that distinguishes time-series data from cross-sectional data.\n\n## How cross-validation is done in the case of Time-series data?\n\nIn the case of time-series data, we cannot choose random samples and assign them to either training or validation set as it makes no sense in using the values from the future data to predict values of the past data.\n\nAs the order of the data is very important for time series related problems, so we split the data into training and validation set according to time, also called as “Forward chaining” method or rolling cross-validation.\n\nWe start with a small subset of data as the training set. Based on that set we predict later data points and then check the accuracy.\n\nThe Predicted samples are then included as part of the next training dataset and subsequent samples are forecasted.","metadata":{}},{"cell_type":"markdown","source":"![ts.png](https://editor.analyticsvidhya.com/uploads/852372020-03-27-image1.png)","metadata":{}},{"cell_type":"markdown","source":"\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#1a8236;overflow:hidden;font-weight:500\"> #   Pros</div><p></br></p>\n\nOne of the finest techniques .\n\n<div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#f00707;overflow:hidden;font-weight:500\"> #   Cons</div><p></br></p>\n\nNot suitable for validation of other data types: As in other techniques we choose random samples as training or validation set, but in this technique order of data is very important.\n\n</br><div style=\"padding:6px;padding-left: 20px;color:white;margin:0;font-size:175%;text-align:left;display:fill;border-radius:4px;background-color:#123475;overflow:hidden;font-weight:500\"> #   Python Code Example</div><p></br></p>","metadata":{}},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.model_selection import TimeSeriesSplit\n\nX = np.array([[1, 2], [3, 4], [1, 2], [3, 4], [1, 2], [3, 4]])\ny = np.array([1, 2, 3, 4, 5, 6])\n\ntime_series = TimeSeriesSplit()\n\nprint(time_series)\n\nfor train_index, test_index in time_series.split(X):\n    print(\"TRAIN:\", train_index, \"TEST:\", test_index)\n    X_train, X_test = X[train_index], X[test_index]\n    y_train, y_test = y[train_index], y[test_index]","metadata":{"execution":{"iopub.status.busy":"2022-05-05T08:14:42.914719Z","iopub.execute_input":"2022-05-05T08:14:42.915096Z","iopub.status.idle":"2022-05-05T08:14:42.933541Z","shell.execute_reply.started":"2022-05-05T08:14:42.915061Z","shell.execute_reply":"2022-05-05T08:14:42.932888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"padding:20px;color:white;margin:0;font-size:250%;text-align:center;display:fill;border-radius:5px;background-color:#4287f5;overflow:hidden;font-weight:500\">References and Related Notebooks</div>","metadata":{}},{"cell_type":"markdown","source":"# References \n- [Top 7 Cross-Validation Techniques with Python Code](https://www.analyticsvidhya.com/blog/2021/11/top-7-cross-validation-techniques-with-python-code/) \n- [Cross-validation (statistics) - Wikipedia](https://en.wikipedia.org/wiki/Cross-validation_(statistics))\n- [Cross validation step by step description](https://stats.stackexchange.com/questions/239414/cross-validation-step-by-step-description)","metadata":{}},{"cell_type":"markdown","source":"# Other Related Notebooks\n- [➡️[Tutorial] 🛠 Feature Engineering ⚙📝](https://www.kaggle.com/code/azminetoushikwasi/tutorial-feature-engineering)\n- [➡️ Intro to Imputation 🔍 Different Techniques](https://www.kaggle.com/code/azminetoushikwasi/intro-to-imputation-different-techniques)\n- [📋 Bias-Variance Tradeoff ➡️ with NumPy & Seaborn](https://www.kaggle.com/code/azminetoushikwasi/bias-variance-tradeoff-with-numpy-seaborn)","metadata":{}},{"cell_type":"markdown","source":"# Fork, Share, Support <3","metadata":{}}]}