| ð ç« è / 模å | âï¸ ææ¯ç¹ | ð å«ä¹ | ð å ³é®ä»£ç | ð§© ç±»æ¯çæ´» | ð¯ è®°å¿å£è¯ |
|---|---|---|---|---|---|
| 1.1.1-1.1.5 æ°æ®åæ |
读åCSV | 读åCSVæä»¶ | pd.read_csv() | æå¼Excelæä»¶ | "è¯»æ°æ®ç¨read_csv" |
| æ¡ä»¶åç±» | æ ¹æ®æ¡ä»¶è¿è¡åç±» | np.where(æ¡ä»¶, çå¼, åå¼) | å¿«éæééåâæ®é/å æ¥â | "æ¡ä»¶åç±»whereï¼npå®¶ä¸ä»¶å¥" | |
| ç»è®¡æ°é | ç»è®¡å段å¼çæ°é | .value_counts() | æ°ä¸æ°ä¸åé¢è²ççæå¤å°ä¸ª | "ç»è®¡æ°évalue_counts" | |
| è®¡ç®æ¯ä¾ | è®¡ç®æä¸ªå¼å æ»æ°çæ¯ä¾ | xxx_counts[...]/len(data) | 计ç®ç级ä¸ç·çå æ¯ | "å æ¯å°±æ¯é¤æ»æ°" | |
| æ°å¼å段 | å°æ°å¼åæä¸åçåºé´ | pd.cut(å, bins=, labels=) | æå¦çææç»©åä¼è¯ä¸å·® | "ååç¨cutï¼binsæ¯åçç¹" | |
| åç»è®¡ç® | åç»åè¿è¡è®¡ç® | .groupby().apply(lambda x: ...) | ç»è®¡æ¯ä¸ªé¨é¨çå¹³åå·¥èµ | "åç»groupbyï¼applyç®æ¯ä¾" | |
| å¡«å ç©ºå¼ | å¡«å æ°æ®ä¸çç©ºå¼ | .fillna() | ç¨å¹³åå填补缺èæç»© | "fillna填补空ï¼ç©ºå¼ä¸åæ" | |
| å 餿°æ® | å 餿°æ®ä¸çè¡æå | .drop() | 廿ä¸éè¦çè´ç©æ¸ å项 | "dropå é¤è¡æå" | |
| ä¿åCSV | å°æ°æ®ä¿å为CSVæä»¶ | .to_csv() | æç¬è®°æ´çæçµåææ¡£ | "æ°æ®å¯¼åºto_csv" | |
| æ£æ¥ç©ºå¼ | æ£æ¥æ°æ®ä¸æ¯å¦åå¨ç©ºå¼ | .isnull() | æ£æ¥è´ç©æ¸ 忝妿鿼 | "isnullæ£æ¥ç©ºï¼é®é¢æ©åç°" | |
| æ£æ¥éå¤ | æ£æ¥æ°æ®ä¸æ¯å¦åå¨éå¤å¼ | .duplicated() | æ£æ¥è´ç©æ¸ 忝妿éå¤é¡¹ | "duplicatedæ¥éå¤ï¼æ°æ®æ´å¹²å" | |
| å åè®¡ç® | å¯¹æ°æ®è¿è¡å åè®¡ç® | .sum() | 计ç®è´ç©æ¸ åæ»éé¢ | "sumæ±å计ç®ï¼æ»æ°è½»æ¾å¾" | |
| æ°æ®ç±»åè½¬æ¢ | è½¬æ¢æ°æ®çç±»å | .astype() | ææåéé¢è½¬æ¢ä¸ºæ°å | "astype转类åï¼æ ¼å¼éå¿å" | |
| 夿èå´ | 夿æ°å¼æ¯å¦å¨æä¸ªèå´å | .between(ä¸é, ä¸é) | å¤ææ¸©åº¦æ¯å¦å¨èéåºé´ | "between夿èå´ï¼ä¸ä¸éåæ" | |
| æ°æ®æ åå | å¯¹æ°æ®è¿è¡æ ååå¤ç | (value - mean) / std | ææç»©æ åå为Zåæ° | "æ ååå¤çï¼åå¼ä¸ºé¶å·®ä¸ºä¸" | |
| 2.1.1-2.1.5 æ°æ®æ¸ æ´ |
å é¤ç©ºå¼ | å 餿°æ®ä¸ç空å¼è¡ | .dropna() | æ¸ æ´æ¿é´æ¶ææä¸ç¨çç©å | "dropnaæ¸ çç©ºï¼æ°æ®æ´çº¯å" |
| æ ååå¤ç | å¯¹æ°æ®è¿è¡æ ååè½¬æ¢ | .fit_transform() | æé£æåæç¸å大å°ä»¥ä¾¿ç¹é¥ª | "fit_transformæ ååï¼æ°æ®æ´é½åè§è" | |
| ååæµè¯é | å°æ°æ®éåå为è®ç»éåæµè¯é | train_test_split() | ææ°´æåæä¸¤é¨åï¼ä¸é¨ååå°ï¼ä¸é¨åç使µè¯ | "train_test_splitåæ°æ®ï¼è®ç»æµè¯ä¸¤ä¸è¯¯" | |
| 读åExcel | 读åExcelæä»¶ | pd.read_excel() | æå¼å¹¶æ¥çExcelçµåè¡¨æ ¼ | "read_excelè¯»è¡¨æ ¼ï¼æ°æ®ä¸ç®äºç¶" | |
| è¡æ°è®¡ç® | è®¡ç®æ°æ®æ¡çè¡æ° | .shape[0] | æ¥çæä»¶çé¡µæ°æ¥äºè§£é¿åº¦ | "shape[0]æ¥è¡æ°ï¼æ°æ®é¿åº¦å¿ä¸ææ°" | |
| å é¤éå¤è¡ | å 餿°æ®ä¸çéå¤è¡ | .drop_duplicates() | 廿è´ç©æ¸ åä¸çéå¤é¡¹ | "drop_duplicateså»éå¤ï¼æ°æ®ç®æ´æ åä½" | |
| åæ®µå¼ | è·åæ°æ®æ¡çåå | .columns | æ¥çè¡¨æ ¼çåæ é¢ | "columnsçåæ®µï¼å忏 æ°åæäº" | |
| å¤çå¼å¸¸å¼ | è¯å«åå¤çå¼å¸¸å¼ | .quantile() | æ¾åºç级æç»©ä¸çå¼å¸¸é«åæä½å | "quantileæ¾å¼å¸¸ï¼æ°æ®å¼å¸¸æ©é¢é²" | |
| ä¿¡æ¯ç»æ | æ¥çæ°æ®çåºæ¬ä¿¡æ¯åç»æ | .info() | æ¥ç书ç±çç®å½åç®ä» | "infoæ¥çç»æï¼æ°æ®ä¿¡æ¯å ¨ææ¡" | |
| éå½å | éå½åæ°æ®æ¡çå | .rename() | ç»æä»¶éæ°å½å以便è¯å« | "renameæ¹ååï¼å忏 æ°å¥½è®°å¿" | |
| 天æ°è®¡ç® | è®¡ç®æ¥æä¹é´ç天æ°å·® | .dt.days | 计ç®ä¸¤ä¸ªæ¥æä¹é´çå¤©æ° | "dt.daysç®å¤©æ°ï¼æ¥æå·®å¼è½»æ¾ç®" | |
| ç»å¾ | ç»å¶æ°æ®å¾è¡¨ | .plot() | ç¨å¾è¡¨å±ç¤ºé宿°æ® | "plotæ¥ç»å¾ï¼æ°æ®å¯è§åä¸ç®äºç¶" | |
| æ£ç¹å¾ | ç»å¶æ£ç¹å¾ | .plot.scatter() | ç¨æ£ç¹å¾å±ç¤ºèº«é«ä¸ä½éçå ³ç³» | "scatterç»æ£ç¹ï¼å ³ç³»æ¨¡å¼çå¾è§" | |
| 饼ç¶å¾ | ç»å¶é¥¼ç¶å¾ | .plot.pie() | ç¨é¥¼ç¶å¾å±ç¤ºé¢ç®åé | "pieç»é¥¼å¾ï¼æ¯ä¾åé 徿¸ æ¥" | |
| 转åä¸ºæ´æ°ç±»å | å°æ°æ®è½¬æ¢ä¸ºæ´æ°ç±»å | .to_numeric() | ææåéé¢è½¬æ¢ä¸ºæ°åä»¥ä¾¿è®¡ç® | "to_numeric转æ°åï¼è®¡ç®æ¹ä¾¿åå¿«æ·" | |
| 2.2.1-2.2.5 æºå¨å¦ä¹ è®ç» |
æ¥çåäºè¡ | æ¥çæ°æ®æ¡çåäºè¡ | .head() | ç¿»é ä¹¦æ¬æ¶å çåå 页 | "headçåå¤´ï¼æ°æ®ä¸ç¼ç " |
| 模åè®ç» | 使ç¨è®ç»æ°æ®è®ç»æ¨¡å | .fit(X_train, y_train) | å¨å¸æç §é£è°±ç¹é¥ª | "fit模åè®ç»å¿ï¼æ°æ®è§å¾å®æ¥å¦" | |
| ä¿å模å | å°è®ç»å¥½ç模åä¿åå°æä»¶ | joblib.dump() æ pickle.dump() | æé£ç©è£ è¿ç½å¤´ä¿å | "dump模åå䏿¥ï¼éæ¶è°ç¨ä¸ç¨ç" | |
| 颿µ | ä½¿ç¨æ¨¡åè¿è¡é¢æµ | .predict() | æ ¹æ®å¤©æ°é¢æ¥å³å®ç©¿è¡£ | "predict颿µæªæ¥ï¼ç»ææåç¥" | |
| æ åå | å¯¹æ°æ®è¿è¡æ ååå¤ç | StandardScaler() | æé£æåæç¸å大å°ä»¥ä¾¿ç¹é¥ª | "StandardScaleræ ååï¼æ°æ®æ´é½åè§è" | |
| 线æ§åå½ | æå»ºçº¿æ§å彿¨¡å | LinearRegression() | ç¨ç´çº¿æåæ°æ®ç¹ | "LinearRegressionç´çº¿æåï¼åå½åæåºç¡å¼º" | |
| 转为èæåé | å°åç±»åé转æ¢ä¸ºæ°å¼åé | pd.get_dummies(X) | ææ°´æç§ç±»è½¬æ¢ä¸ºæ°åç¼ç | "get_dummies转èæï¼åç±»åéæ°å¼å" | |
| åºç¨å½æ° | å¯¹æ°æ®åºç¨èªå®ä¹å½æ° | .apply() | æç §é£è°±æ¥éª¤å¤ç飿 | "apply彿°åºç¨å¹¿ï¼æ°æ®å¤ç徿¹ä¾¿" | |
| åæ¹è¯¯å·® | 计ç®é¢æµå¼ä¸çå®å¼çåæ¹è¯¯å·® | mean_squared_error() | æµéå°å»æç»©çåå·® | "MSEç®è¯¯å·®ï¼å¹³æ¹å¹³ååå·®æ¸ " | |
| å³å®ç³»æ° | 计ç®é¢æµå¼ä¸çå®å¼çå³å®ç³»æ° | r2_score() | è¯ä¼°æ¨¡åè§£éæ°æ®çè½å | "R²çæåï¼è§£éå强弱å¿ä¸æ" | |
| å¹³åç»å¯¹è¯¯å·® | 计ç®é¢æµå¼ä¸çå®å¼çå¹³åç»å¯¹è¯¯å·® | mean_absolute_error() | 计ç®å¤ä¸ªæµéå¼çå¹³ååå·® | "MAEç®åå·®ï¼ç»å¯¹å¼å¹³å徿¸ æ¥" | |
| XGBooståå½ | 使ç¨XGBoostæå»ºå彿¨¡å | xgb.XGBRegressor() | ç¨å¤æç®æ³æé«é¢æµç²¾åº¦ | "XGBRegressorå¼ºç®æ³ï¼åå½é¢æµæ´ç²¾å" | |
| å¦ä¹ ç | 设置模åçå¦ä¹ ç | learning_rate | æ§å¶å¦ä¹ è¿åº¦çå¿«æ ¢ | "learning_rateæ§é度ï¼å¦ä¹ æçèªå·±è°" | |
| æä»¶åå ¥ | æå¼æä»¶å¹¶åå ¥å 容 | with open(report_filename, 'w') as f | æç¬è®°åè¿ç¬è®°æ¬ | "openæä»¶åå å®¹ï¼æ°æ®ä¿åä¸ç¨æ" | |
| 3.2.1-3.2.5 onnx模ååºç¨ |
å 载模å | 使ç¨ONNX Runtimeå 载模å | ort.InferenceSession æ onnxruntime.InferenceSession | å¯å¨æ±½è½¦å¼æåå¤è¡é©¶ | "InferenceSessionå 载模åï¼æ¨ç弿å¯å¨å¿«" |
| å è½½å¾ç | 仿件å è½½å¾ç | Image.open() | æå¼ä¸å¼ ç §çæ¥çå 容 | "Image.openæå¼å¾ï¼å¾çå å®¹å ¨ææ¡" | |
| å¾çé¢å¤ç | 对å¾çè¿è¡é¢å¤ç | preprocess_image() | æ¸ æ´æ°´æä»¥ä¾¿é£ç¨ | "preprocess_imageé¢å¤çï¼å¾çå¹²åè´¨éé«" | |
| æ¨¡åæ¨ç | 使ç¨å è½½çæ¨¡åè¿è¡æ¨ç | session.run() | å»çæ ¹æ®çç¶è¯æç æ | "session.runæ¨¡åæ¨çï¼ç»æå¿«éåç²¾å" | |
| è·åæ¦ç | è·å模åè¾åºçæ¦çå¼ | scipy.special() | ç¨éª°å计ç®è·èæ¦ç | "scipy.specialç®æ¦çï¼æ¨¡åè¾åºæ´æ¸ æ°" | |
| æåº | 对æ°ç»è¿è¡æåº | np.argsort() | æéç«éæèº«é«æåº | "argsortæåºå¿«ï¼é¡ºåºæåä¸ç¨æ" | |
| è°æ´å°ºå¯¸ | è°æ´å¾çç尺寸 | image.resize() | è£åªç §çéåºç¸æ¡ | "image.resizeè°å°ºå¯¸ï¼å¾çéé æ´ç¾è§" | |
| 转æ¢ä¸ºNumPyæ°ç» | å°æ°æ®è½¬æ¢ä¸ºNumPyæ°ç» | np.array() | ææ°´æè£ è¿ç¯®åæ¹ä¾¿æºå¸¦ | "np.array转æ°ç»ï¼æ°æ®å¤çæ´é«æ" | |
| è·åæå¤§å¼ç´¢å¼ | è·åæ°ç»ä¸æå¤§å¼çç´¢å¼ | np.argmax() | æ¾åºç级æé«åçå¦ç | "argmaxæ¾æå¤§ï¼æé«åæ°ä¸ç¼æ" | |
| æ·»å 维度 | ç»æ°ç»å¢å ä¸ä¸ªç»´åº¦ | np.expand_dims() | ç»çåå ä¸å±å è£ | "expand_dimsæ·»ç»´åº¦ï¼æ°æ®ç»ææ´çµæ´»" | |
| è·åè¾å ¥å¼ éåç§° | è·å模åè¾å ¥å¼ éçåç§° | session.get_inputs()[0].name | æ¥çé£è°±ä¸ç主è¦é£æ | "get_inputsæ¥è¾å ¥ï¼æ¨¡åéæ±æ©ç¥é" | |
| è·åæ 绪æ ç¾ | ä»åå ¸ä¸è·å对åºçæ 绪æ ç¾ | list(emotion_table.keys())[predicted_label] | æ ¹æ®ç¼å·æ¾å°å¯¹åºçæ 绪 | "åå ¸è½¬åè¡¨æ¥æ ç¾ï¼æ 绪è¯å«æ´ç´è§" |