34:["$","title",null,{"children":"Learning to predict Wine quality using TF.js and Danfo.js | Bamigbade Opeyemi | Observable"}] 3c:[{"id":"619c7e1485f4f02e9f0f856792dbc135470d5d9d4197fd48e2922e3055b1756e88e5823d619b5720865d0620fa81d33c74277e2cbf9b450866176b3aabb48d20","href":"https://static.observableusercontent.com/files/619c7e1485f4f02e9f0f856792dbc135470d5d9d4197fd48e2922e3055b1756e88e5823d619b5720865d0620fa81d33c74277e2cbf9b450866176b3aabb48d20","name":"wine_dataset.csv","type":"text/csv","lastModified":1597309973460.603,"size":390376}] 38:{"id":"162f47440bfe1f2f","slug":"learning-to-predict-wine-quality-using-tf-js-and-danfo-js","title":"Learning to predict Wine quality using TF.js and Danfo.js","thumbnail":"65f66b9ff95aa1827b3cb57bd1fbd5a08e18f886eb7ef655bb1381d240e166bb","access_level":"public","create_time":"$D2020-08-13T09:07:42.229Z","update_time":"$D2020-08-26T05:52:23.269Z","view_time":null,"first_public_time":"$D2020-08-26T05:54:35.188Z","has_unpublished_edits":null,"fork":{"id":"ee226c3329e1b146","slug":"learning-to-predict-iris-species-using-tf-js-and-danfo-js","title":"Learning to predict Iris species using TF.js and Danfo.js","owner":{"id":"3df8ffe3d85471be","login":"napsternxg","name":"Shubhanshu Mishra"}},"stars":8,"starred":false,"owner":{"type":"team","id":"c0a4547d38c1b5a2","login":"opeyemibami","name":"Bamigbade Opeyemi","avatar_url":"https://avatars-next.observableusercontent.com/11028c4c686d7f940e282e6b07e4eee65712af4b6ada786261b883a908de9340","tier":"starter_2024","bio":"","followed_by_you":false,"follows_you":false},"version":1823,"publish_version":1823,"role":null,"authored":false,"authors":[{"type":"individual","id":"db551840d7712723","login":"opeyemibami","name":"Bamigbade Opeyemi","avatar_url":"https://avatars-next.observableusercontent.com/11028c4c686d7f940e282e6b07e4eee65712af4b6ada786261b883a908de9340","tier":null,"bio":"","followed_by_you":false,"follows_you":false}],"members":[{"type":"individual","id":"db551840d7712723","login":"opeyemibami","name":"Bamigbade Opeyemi","avatar_url":"https://avatars-next.observableusercontent.com/11028c4c686d7f940e282e6b07e4eee65712af4b6ada786261b883a908de9340","tier":null,"role":"editor"}],"comments":[{"id":"ddb8f6af939a84f4","reply_to_id":null,"content":"# import danfo.js","create_time":"$D2020-08-16T19:46:52.020Z","update_time":null,"resolved":true,"user":{"type":"individual","id":"db551840d7712723","login":"opeyemibami","name":"Bamigbade Opeyemi","avatar_url":"https://avatars-next.observableusercontent.com/11028c4c686d7f940e282e6b07e4eee65712af4b6ada786261b883a908de9340","tier":null}}],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":6,"collection":null,"type":"notebook","body":{"titling":"auto","title":"Learning to predict Wine quality using TF.js and Danfo.js","cells":[{"id":0,"value":"md`# Learning to predict Wine quality using TF.js and Danfo.js\nDanfo.js is the best javascript package that provides fast, flexible, and expressive data structures designed to make working with \"relational\" or \"labelled\" data both easy and intuitive. It is heavily inspired by the Pandas library and provides a similar API.\n### Important !!!\n* The tutorial aim at introducing you to capabilities of Danfo.js and TF.js \n* Get familiar with observable nootbook as it is different from jupyter notebook via https://observablehq.com/@observablehq/observable-for-jupyter-users\n* Uncomment a cell and run it with \"Shift + Enter\" one at a time to avoid errors \n* Have fun !\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1363,"value":"md`\n## Lets get started\nimport danfo.js and TF.js\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":2,"value":"dfd = require('danfojs@0.0.15/dist/index.min.js').catch(() => {\n window.dfd.Series.prototype.print = window.dfd.DataFrame.prototype.print = function() { return print(this) };\n return window.dfd;\n})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1360,"value":"tf = require('@tensorflow/tfjs')","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1430,"value":"md`\n### Data ingestion \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":96,"value":"df = dfd.read_csv(await FileAttachment(\"wine_dataset.csv\").url())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":101,"value":"print(df.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1445,"value":"df.shape","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":141,"value":"md`\n### column renaming \nRenaming \"type\" feature to \"wine_type\"\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":570,"value":"// df1 = df.rename({mapper:{'type':'wine_type'}})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":572,"value":"// print(df1.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1444,"value":"md`\n### Data preprocessing and EDA\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":153,"value":"// print(df1.describe())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":176,"value":"// print(df1.isna().sum())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1453,"value":"md`\n### Percentage of missing data \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":168,"value":"// print(df1.isna().sum().div(df1.isna().count()).round(4))","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1466,"value":"md`\n### fill missing values mean \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":185,"value":"// df_filled = {\n// let df2\n// df1.columns.forEach(function(feat,i){\n// if(df1[feat].dtypes[0]!=\"string\"){\n// let mean = Number(df1[feat].mean().toFixed(4))\n// df2 = df1.fillna({columns:[feat],values:[mean]})\n// }\n \n// }) \n// return df2\n// }\n ","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":236,"value":"// print(df_filled.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":245,"value":"// print(df_filled.isna().sum())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1472,"value":"md`\n### Encode wine_type to numbers \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":535,"value":"// dum_df = {\n// let df1 = df_filled.replace({\"replace\": \"white\", \"with\": 0, \"in\": [\"wine_type\"]}) \n// let df2 = df1.replace({\"replace\": \"red\", \"with\": 1, \"in\": [\"wine_type\"]})\n// df2.astype({column: \"wine_type\", dtype: \"int32\"})\n// return df2\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":539,"value":" // print(dum_df.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":285,"value":"// print(dum_df.ctypes)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1478,"value":"md`\n### The \"div\" function for plotting \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":294,"value":"// function div(fn) {\n// const d = html`

`;\n// fn(d);\n// return d;\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1481,"value":"md`\n### Visualizations for EDA\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":299,"value":"// dum_df.quality.nunique()","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":345,"value":"// print(dum_df.quality.value_counts())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":297,"value":"// {\n// let layout = {\n// title: 'Wine Quality Counts Plot',\n// }\n// let quality_count = dum_df.quality.value_counts()\n// return div(d => quality_count.plot(d).bar({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":419,"value":"// {\n// let layout = {\n// title: 'wine quality proportion',\n// }\n// let quality_count = dum_df.quality.value_counts()\n// return div(d => quality_count.plot(d).pie({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":422,"value":"md`\n### Binning the target feature\nhere 6 wine quality values based from the results above. Minimum is 3 and maximum is 9. We can create 3 wine quality categories namely poor quality, normal quality, excellent quality.\n\n* if quality < 6 - poor quality\n* if quality = 6 - normal quality\n* if quality > 6 - excellent quality\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":427,"value":"// {\n// let mapper = {1:0,2:0,3:0,4:0,5:0,6:1,7:2,8:2,9:2}\n// let new_cols = dum_df['quality'].map(mapper).values\n// dum_df.addColumn({ \"column\": \"wine_quality\", \"value\": new_cols })\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":581,"value":"// print(dum_df.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1495,"value":"md`\n### drop \"quality\" after binning \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":455,"value":"// df4 = dum_df.drop({ columns: [\"quality\"], axis: 1, inplace: false})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":467,"value":"// print(df4.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":470,"value":"// {\n// let layout = {\n// title: 'newly grouped wine quality bar plot',\n// xaxis: {\n// title: 'wine quality',\n// },\n// yaxis: {\n// title: 'counts',\n// }\n// }\n// let quality_count = df4.wine_quality.value_counts()\n// return div(d => quality_count.plot(d).bar({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1503,"value":"md`\n### Feature distribution \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":363,"value":"// {\n// let layout = {\n// title: 'fixed acidity Distribution',\n// }\n// return div(d => dum_df['fixed acidity'].plot(d).hist({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":368,"value":"// {\n// let layout = {\n// title: 'fixed acidity Distribution',\n// }\n// return div(d => df4['volatile acidity'].plot(d).hist({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1509,"value":"md`\n### Feature relationship to target feature visualization \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":510,"value":"// {\n// let layout = {\n// title: 'fixed acidity relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"fixed acidity\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":512,"value":"// {\n// let layout = {\n// title: 'volatile acidity relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"volatile acidity\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":514,"value":"// {\n// let layout = {\n// title: 'citric acid relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"citric acid\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":516,"value":"// {\n// let layout = {\n// title: 'residual sugar relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"residual sugar\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":518,"value":"// {\n// let layout = {\n// title: 'chlorides relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"chlorides\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":520,"value":"// {\n// let layout = {\n// title: 'free sulfur dioxide relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"free sulfur dioxide\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":522,"value":"// {\n// let layout = {\n// title: 'total sulfur dioxide relationship to target feature',\n// }\n// return div(d => df4.plot(d).bar({x:\"wine_quality\",y:\"total sulfur dioxide\",layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":383,"value":"// print(df4.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":483,"value":"// {\n// let sub_df = df4.loc({ columns: [\"fixed acidity\",\"volatile acidity\", \"citric acid\",\"residual sugar\",\"chlorides\",\n// \"free sulfur dioxide\",\"total sulfur dioxide\",\"density\",\"pH\",\"alcohol\"] })\n// let layout = {\n// title: 'features box plot before scaling', xaxis: {title: 'X',},yaxis: {title: 'Y',\n// }\n// }\n// return div(d => sub_df.plot(d).box({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1539,"value":"md`\n### Data Scaling\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":740,"value":"// df_scaled = {\n// let scaler = new dfd.MinMaxScaler()\n// let X = df4.iloc({ columns: [\"0:11\"] })\n// scaler.fit(X)\n// let scaled_df = scaler.transform(X)\n// return new dfd.DataFrame(scaled_df.values,{columns: df4.columns.slice(0,12)}).round(4)\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":752,"value":"// print(df_scaled.tail())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1545,"value":"md` #### Add target feature to the dataframe`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":855,"value":"// df_scaled.addColumn({ \"column\": \"wine_quality\", \"value\": df4.wine_quality.values })","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":783,"value":"// print(df_scaled.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":824,"value":"// {\n// let sub_df = df_scaled.loc({ columns: [\"fixed acidity\",\"volatile acidity\", \"citric acid\",\"residual sugar\",\"chlorides\",\n// \"free sulfur dioxide\",\"total sulfur dioxide\",\"density\",\"pH\",\"alcohol\"] })\n// let layout = {\n// title: 'box plot of scaled dataset', xaxis: {title: 'X',},yaxis: {title: 'Y',\n// }\n// }\n// return div(d => sub_df.plot(d).box({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1034,"value":"// print(df_scaled.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1555,"value":"md`\n# OneHotEncoding of the target feature since its a multiclass\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1036,"value":"// y_hot = {\n// let encode = new dfd.OneHotEncoder()\n// let y = df_scaled[\"wine_quality\"].values\n// encode.fit(y)\n// let y_enc = encode.transform(y)\n// return y_enc\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1052,"value":"// print(y_hot)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1077,"value":"md`\n### merge X with encoded y\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1066,"value":"// df5 = {\n// let X = df_scaled.drop({ columns: [\"wine_quality\"], axis: 1, inplace: false})\n// let com_df = dfd.concat({ df_list: [X, y_hot], axis: 1 })\n// return com_df\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1072,"value":"// print(df5.head())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":587,"value":"// n_rows = df_scaled.shape[0]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1575,"value":"md`\n### Train Test splitting for model training and evaluation \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":593,"value":"// train_test_split = { let df_len = df_scaled.shape[0]\n// let df_sample = df5.sample(df_len)\n// let X = df5.iloc({columns: [\"0:11\"]})\n// let y = df5.iloc({columns: [\"12:\"]})\n// let X_train = X.iloc({rows: [\"0:4999\"]}).tensor\n// let y_train = y.iloc({rows: [\"0:4999\"]}).tensor\n// let X_test = X.iloc({rows: [\"4999:\"]}).tensor\n// let y_test = y.iloc({rows: [\"4999:\"]}).tensor\n// let data_array = [X_train,X_test,y_train,y_test]\n// return data_array\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":736,"value":"// train_test_split[1].shape","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":599,"value":"// get input shape for MLP\n// input_shape = train_test_split[0].shape[1]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":88,"value":"// training_stats = {\n// return {\n// accuracy: 0,\n// val_acc:0,\n// }\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1586,"value":"md`\n### Instatiate MLP model with TF.js\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":44,"value":"// model = {\n\n// // Define a model for linear regression.\n// const model = tf.sequential({\n// layers: [\n// tf.layers.dense({inputShape: [input_shape], units: 32, activation: 'relu'}),\n// tf.layers.dense({units: 64, activation: 'relu'}),\n// tf.layers.dense({units: 128, activation: 'relu'}),\n// tf.layers.dense({units: 64, activation: 'relu'}),\n// tf.layers.dense({units: 32, activation: 'relu'}),\n// tf.layers.dense({units: 3, activation: 'softmax'}),\n// ]\n// });\n\n// // Prepare the model for training: Specify the loss and the optimizer.\n// model.compile({\n// optimizer: 'sgd',\n// loss: 'categoricalCrossentropy',\n// metrics: ['accuracy'],\n// });\n \n// return model\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1647,"value":"// // array for evaluation plotting \n// validation_acc = []","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1265,"value":"// // array for evaluation plotting \n// training_acc = []\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1594,"value":"md`\n### fit model on X_train and y_train with 20% validation split\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":52,"value":"// model.fit(train_test_split[0], train_test_split[2], {\n// epochs: 100,\n// batchSize: 32,\n// validationSplit: 0.2,\n \n// callbacks: {onEpochEnd: (batch, logs) => {\n \n// training_acc.push(logs.acc)\n// validation_acc.push(logs.val_acc)\n \n// }, callbacks :tf.callbacks.earlyStopping({monitor: 'val_acc'})}\n// }).then(info => {\n \n// });\n ","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1599,"value":"md` ### Create dataframe for evaluation\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1256,"value":"// df_eva = {\n// let data = {\"train_acc\":training_acc,\"val_acc\":validation_acc}\n// let df_output = new dfd.DataFrame(data)\n// return df_output\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1605,"value":"md` \n### Model evaluation\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1286,"value":"// {\n// let layout = {\n// title: 'Model Evaluation',\n// xaxis: {\n// title: 'Number of Epochs',\n// },\n// yaxis: {\n// title: 'Accuracy',\n// }\n// }\n// return div(d => df_eva.plot(d).line({layout:layout}))\n// }","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":74,"value":"// model.evaluate(train_test_split[1],train_test_split[3])","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":707,"value":"function print(df) {\n const {col_types, series, columns, index, values} = df;\n const table = html`\n

\n \n \n \n \n ${series\n ? html``\n : columns.map((name, i) => html``)}\n \n \n \n ${values.map((row, i) => html`\n \n \n ${series\n ? html``\n : row.map((v, j) => html``)}\n \n `)}\n \n

	${columns}	${name}
${index[i]}	${row}	${v}

\n \n `;\n table.value = df;\n return table;\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":9,"value":"// import {print} from \"@visnup/hello-danfo-js\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1357,"value":"md`# References \n \n* Code for danfo.js inspiration from : https://observablehq.com/@visnup/hello-danfo-js\n* Code for TF.js inspiration from: https://www.tensorflow.org/js/guide/train_models\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W3c","stdlib":"1"}} 33:null