[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H9RNTRRC9KENGX1SCXV9F2":3,"skill-same:01M6H9RNTRRC9KENGX1SCXV9F2":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6H9RNTRRC9KENGX1SCXV9F2","feature-engineering",null,"Machine learning feature engineering","NeuralBlitz\u002FMito","NeuralBlitz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F79354388?v=4","01M6H8T2TFH477HRS0KTSTKR2E","David Riggs","01M6H8T2YQQDXPYM092P670Z21",0,"MIT","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Ffeature-engineering\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"feature engineering","engineering","feature","machine learning","data","machine-learning","science","learning","opencode","data-science","machine","2026-11-10 10:12:30",false,"---\nname: feature-engineering\ndescription: Machine learning feature engineering\nlicense: MIT\ncompatibility: opencode\nmetadata:\n  audience: machine-learning-engineers\n  category: data-science\n---\n\n## What I do\n\n- Create features from raw data for ML models\n- Transform variables for better model performance\n- Handle categorical and numerical features\n- Create interaction and polynomial features\n- Extract features from text, dates, and images\n- Handle missing data strategically\n- Select most predictive features\n\n## When to use me\n\nUse me when:\n- Preparing data for ML models\n- Improving model performance\n- Working with raw\u002Funstructured data\n- Handling complex data types\n- Reducing feature dimensionality\n\n## Key Concepts\n\n### Feature Engineering Techniques\n```python\nimport pandas as pd\nimport numpy as np\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.impute import SimpleImputer\n\n# Numerical transformations\ndf[\"log_income\"] = np.log1p(df[\"income\"])\ndf[\"income_squared\"] = df[\"income\"] ** 2\ndf[\"income_bucket\"] = pd.cut(df[\"income\"], bins=[0, 30, 60, 100], \n                              labels=[\"low\", \"mid\", \"high\"])\n\n# Date features\ndf[\"order_date\"] = pd.to_datetime(df[\"order_date\"])\ndf[\"order_year\"] = df[\"order_date\"].dt.year\ndf[\"order_month\"] = df[\"order_date\"].dt.month\ndf[\"order_dayofweek\"] = df[\"order_date\"].dt.dayofweek\ndf[\"is_weekend\"] = df[\"order_dayofweek\"].isin([5, 6]).astype(int)\n\n# Aggregation features\nuser_stats = df.groupby(\"user_id\").agg({\n    \"order_id\": \"count\",\n    \"total_amount\": [\"sum\", \"mean\", \"std\"],\n    \"order_date\": [\"min\", \"max\"]\n}).reset_index()\n\n# Merge back\ndf = df.merge(user_stats, on=\"user_id\", how=\"left\")\n\n# Text features\ndf[\"title_length\"] = df[\"title\"].str.len()\ndf[\"word_count\"] = df[\"title\"].str.split().str.len()\ndf[\"has_exclamation\"] = df[\"title\"].str.contains(\"!\").astype(int)\n\n# Categorical encoding\n# One-hot encoding\npd.get_dummies(df, columns=[\"category\"], prefix=\"cat\")\n\n# Target encoding\nmean_encoding = df.groupby(\"category\")[\"target\"].mean()\ndf[\"category_encoded\"] = df[\"category\"].map(mean_encoding)\n```\n\n### Feature Selection\n- **Filter methods**: Correlation, chi-square\n- **Wrapper methods**: RFE, forward selection\n- **Embedded methods**: LASSO, feature importance\n\n### Handling Imbalanced Data\n- SMOTE oversampling\n- Undersampling majority class\n- Class weights in model\n- Focal loss\n","## What I do\n\n- Create features from raw data for ML models\n- Transform variables for better model performance\n- Handle categorical and numerical features\n- Create interaction and polynomial features\n- Extract features from text, dates, and images\n- Handle missing data strategically\n- Select most predictive features\n\n## When to use me\n\nUse me when:\n- Preparing data for ML models\n- Improving model performance\n- Working with raw\u002Funstructured data\n- Handling complex data types\n- Reducing feature dimensionality\n\n## Key Concepts\n\n### Feature Engineering Techniques\n```python\nimport pandas as pd\nimport numpy as np\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.impute import SimpleImputer\n\n# Numerical transformations\ndf[\"log_income\"] = np.log1p(df[\"income\"])\ndf[\"income_squared\"] = df[\"income\"] ** 2\ndf[\"income_bucket\"] = pd.cut(df[\"income\"], bins=[0, 30, 60, 100], \n                              labels=[\"low\", \"mid\", \"high\"])\n\n# Date features\ndf[\"order_date\"] = pd.to_datetime(df[\"order_date\"])\ndf[\"order_year\"] = df[\"order_date\"].dt.year\ndf[\"order_month\"] = df[\"order_date\"].dt.month\ndf[\"order_dayofweek\"] = df[\"order_date\"].dt.dayofweek\ndf[\"is_weekend\"] = df[\"order_dayofweek\"].isin([5, 6]).astype(int)\n\n# Aggregation features\nuser_stats = df.groupby(\"user_id\").agg({\n    \"order_id\": \"count\",\n    \"total_amount\": [\"sum\", \"mean\", \"std\"],\n    \"order_date\": [\"min\", \"max\"]\n}).reset_index()\n\n# Merge back\ndf = df.merge(user_stats, on=\"user_id\", how=\"left\")\n\n# Text features\ndf[\"title_length\"] = df[\"title\"].str.len()\ndf[\"word_count\"] = df[\"title\"].str.split().str.len()\ndf[\"has_exclamation\"] = df[\"title\"].str.contains(\"!\").astype(int)\n\n# Categorical encoding\n# One-hot encoding\npd.get_dummies(df, columns=[\"category\"], prefix=\"cat\")\n\n# Target encoding\nmean_encoding = df.groupby(\"category\")[\"target\"].mean()\ndf[\"category_encoded\"] = df[\"category\"].map(mean_encoding)\n```\n\n### Feature Selection\n- **Filter methods**: Correlation, chi-square\n- **Wrapper methods**: RFE, forward selection\n- **Embedded methods**: LASSO, feature importance\n\n### Handling Imbalanced Data\n- SMOTE oversampling\n- Undersampling majority class\n- Class weights in model\n- Focal loss\n",{"name":5,"license":15,"metadata":35,"description":7,"compatibility":27},{"audience":36,"category":28},"machine-learning-engineers","main","2ea764e153842704d24a2e9aa4170441a7f03081",".opencode\u002Fskills\u002Ffeature-engineering","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito","https:\u002F\u002Fgithub.com\u002FNeuralBlitz","nuralnexus.org","Theoretical and Futuristic AI Nerd 🤓 ","2026-11-12 03:13:05",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add NeuralBlitz\u002FMito --skill feature-engineering",{"tool":51,"command":52},"bunx","bunx skills add NeuralBlitz\u002FMito --skill feature-engineering",{"tool":54,"command":55},"pnpm","pnpm dlx skills add NeuralBlitz\u002FMito --skill feature-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Ffeature-engineering\u002FSKILL.md",true,[],[60,75,88,101,109,134],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":30},"01M6HAZSAQK1S27CEZYAYJTQDX","wireless-communications","Wireless systems, mobile networks, and 5G\u002F6G","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fwireless-communications\u002FSKILL.md",[],[67,68,69,70,20,71,72,73,27,74],"communications","wireless communications","wireless","systems","networks","5G","students","mobile",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":30},"01M6HAZFX6E8NK3WZWDX5YCKYY","websockets","WebSocket implementation and best practices","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fwebassembly\u002Fwebsockets\u002FSKILL.md",[],[77,82,83,84,27,85,86,87],"websocket implementation","time","implementation","real-time","websocket","best practices",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":30},"01M6HAZ6DAXBQ7QHXXM1EM7715","vulnerability-auditing","Vulnerability assessment and auditing","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fvulnerability-auditing\u002FSKILL.md",[],[95,96,97,98,27,99,100],"vulnerability","vulnerability auditing","security","vulnerability assessment","cybersecurity","assessment",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":30},"01M6HAZ3FKF3CS9Z3J96RVE2ZE","vulnerability-assessment","Finding and assessing security vulnerabilities","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fvue\u002Fvulnerability-assessment\u002FSKILL.md",[],[98,95,100,97,108,27],"vulnerabilities",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":125,"publishedAt":30},"01M6HAYSHM6HKRKEHFP0SGZQX7","vlsi-design","Very-Large-Scale Integration circuit design and semiconductor engineering","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fvlsi-design\u002FSKILL.md",[115,120],{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[126,127,128,129,130,20,131,27,132,73,133],"vlsi design","VLSI","design","hardware","integration","computer","scale","circuit",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":30},"01M6HAYPQ30FFE2JXD7WQJ8R6C","unsupervised","Unsupervised learning concepts","https:\u002F\u002Fgithub.com\u002FNeuralBlitz\u002FMito\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fvisualization\u002Funsupervised\u002FSKILL.md",[],[136,26,27,141,142,29,143,24],"intelligence","unsupervised learning","concepts"]