{"id":42202,"date":"2025-06-06T18:26:01","date_gmt":"2025-06-06T10:26:01","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/42202.html"},"modified":"2025-06-06T18:26:01","modified_gmt":"2025-06-06T10:26:01","slug":"kaggle-predicting-optimal-fertilizers-%e5%a4%9a%e5%88%86%e7%b1%bbxgboost","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/42202.html","title":{"rendered":"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost)"},"content":{"rendered":"

Predicting Optimal Fertilizers<\/p>\n

\u9898\u610f：<\/h6>\n

\u7ed9\u51fa\u571f\u58e4\u7684\u7279\u6027，\u9884\u6d4b\u51fa3\u79cd\u6700\u4f73\u7684\u80a5\u6599<\/p>\n

\u6570\u636e\u5904\u7406：<\/h6>\n

1.\u6709\u6570\u5b57\u578b\u548c\u7c7b\u522b\u578b，\u7c7b\u522b\u4e0d\u80fd\u968f\u610f\u6362\u6210\u6570\u5b57，\u72ec\u70ed\u7f16\u7801\u3002cat\u53ef\u4ee5\u76f4\u63a5\u5904\u7406category\u7c7b\u578b\u3002 2.\u6784\u9020\u4e00\u4e9b\u76f8\u5173\u571f\u58e4\u7279\u6027\u7279\u5f81 3.\u7531\u4e8elabel\u662fcategory\u7c7b\u578b，\u4f46\u662fxgb\u4e0d\u53ef\u4ee5\u5904\u7406category\u7c7b\u578b，\u56e0\u6b64\u9700\u8981\u5148\u7f16\u7801，\u6700\u540e\u6c42\u51fa\u7ed3\u679c\u4e4b\u540e\u518d\u89e3\u7801\u3002<\/p>\n

\u5efa\u7acb\u6a21\u578b：<\/h6>\n

1.catboost\u4ea4\u53c9\u9a8c\u8bc1\u3001xgboost\u4ea4\u53c9\u9a8c\u8bc1<\/p>\n

\u4ee3\u7801：<\/h6>\n

import<\/span> os
\nimport<\/span> warnings
\nimport<\/span> numpy as<\/span> np
\nimport<\/span> pandas as<\/span> pd
\nfrom<\/span> sklearn.<\/span>model_selection import<\/span> StratifiedKFold
\nfrom<\/span> sklearn.<\/span>preprocessing import<\/span> LabelEncoder
\nfrom<\/span> xgboost import<\/span> XGBClassifier
\nfrom<\/span> catboost import<\/span> CatBoostClassifier
\nfrom<\/span> lightgbm import<\/span> LGBMClassifier
\nfrom<\/span> sklearn.<\/span>metrics import<\/span> accuracy_score<\/p>\n

# \u5ffd\u7565\u8b66\u544a\u4fe1\u606f<\/span>
\nwarnings.<\/span>filterwarnings(<\/span>'ignore'<\/span>)<\/span>
\nos.<\/span>environ[<\/span>'TF_CPP_MIN_LOG_LEVEL'<\/span>]<\/span> =<\/span> '3'<\/span><\/p>\n

def<\/span> init<\/span>(<\/span>)<\/span>:<\/span>
\n """\u521d\u59cb\u5316\u8bbe\u7f6e"""<\/span>
\n pd.<\/span>set_option(<\/span>'display.width'<\/span>,<\/span> 1000<\/span>)<\/span>
\n pd.<\/span>set_option(<\/span>'display.max_colwidth'<\/span>,<\/span> 1000<\/span>)<\/span>
\n pd.<\/span>set_option(<\/span>"display.max_rows"<\/span>,<\/span> 1000<\/span>)<\/span>
\n pd.<\/span>set_option(<\/span>"display.max_columns"<\/span>,<\/span> 1000<\/span>)<\/span><\/p>\n

def<\/span> load_data<\/span>(<\/span>path_train,<\/span> path_test)<\/span>:<\/span>
\n """\u52a0\u8f7d\u6570\u636e"""<\/span>
\n df_train =<\/span> pd.<\/span>read_csv(<\/span>path_train)<\/span>
\n df_test =<\/span> pd.<\/span>read_csv(<\/span>path_test)<\/span>
\n print<\/span>(<\/span>f"Train shape: <\/span>{<\/span>df_train.<\/span>shape}<\/span><\/span>, Test shape: <\/span>{<\/span>df_test.<\/span>shape}<\/span><\/span>"<\/span><\/span>)<\/span>
\n return<\/span> df_train,<\/span> df_test<\/p>\n

def<\/span> feature_engineering<\/span>(<\/span>df_all)<\/span>:<\/span>
\n """\u7279\u5f81\u5de5\u7a0b：\u521b\u5efa\u65b0\u7279\u5f81"""<\/span>
\n # \u80a5\u529b\u7efc\u5408\u6307\u6570<\/span>
\n df_all[<\/span>'Fertility_Index'<\/span>]<\/span> =<\/span> (<\/span>0.4<\/span> *<\/span> df_all[<\/span>'Nitrogen'<\/span>]<\/span> \/<\/span> 100<\/span> +<\/span>
\n 0.3<\/span> *<\/span> df_all[<\/span>'Phosphorous'<\/span>]<\/span> \/<\/span> 50<\/span> +<\/span>
\n 0.3<\/span> *<\/span> df_all[<\/span>'Potassium'<\/span>]<\/span> \/<\/span> 150<\/span>)<\/span>
\n # \u6c2e\u78f7\u6bd4<\/span>
\n df_all[<\/span>'N_P_ratio'<\/span>]<\/span> =<\/span> df_all[<\/span>'Nitrogen'<\/span>]<\/span> \/<\/span> (<\/span>df_all[<\/span>'Phosphorous'<\/span>]<\/span> +<\/span> 1e-6<\/span>)<\/span>
\n # \u94be\u7d20\u76c8\u4e8f\u5dee<\/span>
\n df_all[<\/span>'K_deficit'<\/span>]<\/span> =<\/span> df_all[<\/span>'Potassium'<\/span>]<\/span> –<\/span> (<\/span>df_all[<\/span>'Nitrogen'<\/span>]<\/span> +<\/span> df_all[<\/span>'Phosphorous'<\/span>]<\/span>)<\/span> \/<\/span> 2<\/span><\/p>\n

# \u7c7b\u522b\u7f16\u7801<\/span>
\n df_all[<\/span>'Crop_Type_Code'<\/span>]<\/span> =<\/span> LabelEncoder(<\/span>)<\/span>.<\/span>fit_transform(<\/span>df_all[<\/span>'Crop Type'<\/span>]<\/span>)<\/span>
\n category_data =<\/span> pd.<\/span>get_dummies(<\/span>df_all[<\/span>[<\/span>'Soil Type'<\/span>,<\/span> 'Crop Type'<\/span>]<\/span>]<\/span>)<\/span>
\n df_all =<\/span> pd.<\/span>concat(<\/span>[<\/span>df_all.<\/span>drop(<\/span>[<\/span>'Soil Type'<\/span>,<\/span> 'Crop Type'<\/span>]<\/span>,<\/span> axis=<\/span>1<\/span>)<\/span>,<\/span> category_data]<\/span>,<\/span> axis=<\/span>1<\/span>)<\/span><\/p>\n

return<\/span> df_all<\/p>\n

def<\/span> prepare_data<\/span>(<\/span>df_train,<\/span> df_test)<\/span>:<\/span>
\n """\u5408\u5e76\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\u5e76\u8fdb\u884c\u9884\u5904\u7406"""<\/span>
\n df_all =<\/span> pd.<\/span>concat(<\/span>[<\/span>
\n df_train.<\/span>drop(<\/span>[<\/span>'id'<\/span>,<\/span> 'Fertilizer Name'<\/span>]<\/span>,<\/span> axis=<\/span>1<\/span>)<\/span>,<\/span>
\n df_test.<\/span>drop(<\/span>[<\/span>'id'<\/span>]<\/span>,<\/span> axis=<\/span>1<\/span>)<\/span>
\n ]<\/span>,<\/span> axis=<\/span>0<\/span>)<\/span>.<\/span>reset_index(<\/span>drop=<\/span>True<\/span>)<\/span><\/p>\n

df_all =<\/span> feature_engineering(<\/span>df_all)<\/span><\/p>\n

X_train =<\/span> df_all[<\/span>:<\/span>len<\/span>(<\/span>df_train)<\/span>]<\/span>
\n Y_train =<\/span> LabelEncoder(<\/span>)<\/span>.<\/span>fit_transform(<\/span>df_train[<\/span>'Fertilizer Name'<\/span>]<\/span>)<\/span>
\n X_test =<\/span> df_all[<\/span>len<\/span>(<\/span>df_train)<\/span>:<\/span>]<\/span><\/p>\n

return<\/span> X_train,<\/span> Y_train,<\/span> X_test<\/p>\n

def<\/span> train_model<\/span>(<\/span>X_train,<\/span> Y_train,<\/span> model_type=<\/span>'xgb'<\/span>,<\/span> n_splits=<\/span>5<\/span>)<\/span>:<\/span>
\n """\u4f7f\u7528\u4ea4\u53c9\u9a8c\u8bc1\u8bad\u7ec3\u6a21\u578b"""<\/span>
\n models =<\/span> [<\/span>]<\/span>
\n oof_preds =<\/span> np.<\/span>zeros(<\/span>(<\/span>X_train.<\/span>shape[<\/span>0<\/span>]<\/span>,<\/span>)<\/span>)<\/span>
\n scores =<\/span> [<\/span>]<\/span><\/p>\n

kfold =<\/span> StratifiedKFold(<\/span>n_splits=<\/span>n_splits,<\/span> shuffle=<\/span>True<\/span>,<\/span> random_state=<\/span>42<\/span>)<\/span><\/p>\n

for<\/span> fold,<\/span> (<\/span>train_idx,<\/span> val_idx)<\/span> in<\/span> enumerate<\/span>(<\/span>kfold.<\/span>split(<\/span>X_train,<\/span> Y_train)<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>f"\\\\nFold <\/span>{<\/span>fold +<\/span> 1<\/span>}<\/span><\/span>\/<\/span>{<\/span>n_splits}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

x_tr,<\/span> x_val =<\/span> X_train.<\/span>iloc[<\/span>train_idx]<\/span>,<\/span> X_train.<\/span>iloc[<\/span>val_idx]<\/span>
\n y_tr,<\/span> y_val =<\/span> Y_train[<\/span>train_idx]<\/span>,<\/span> Y_train[<\/span>val_idx]<\/span><\/p>\n

if<\/span> model_type ==<\/span> 'xgb'<\/span>:<\/span>
\n model =<\/span> XGBClassifier(<\/span>
\n max_depth=<\/span>12<\/span>,<\/span>
\n colsample_bytree=<\/span>0.467<\/span>,<\/span>
\n subsample=<\/span>0.86<\/span>,<\/span>
\n n_estimators=<\/span>8000<\/span>,<\/span>
\n learning_rate=<\/span>0.03<\/span>,<\/span>
\n gamma=<\/span>0.26<\/span>,<\/span>
\n max_delta_step=<\/span>4<\/span>,<\/span>
\n reg_alpha=<\/span>2.7<\/span>,<\/span>
\n reg_lambda=<\/span>1.4<\/span>,<\/span>
\n early_stopping_rounds=<\/span>500<\/span>,<\/span>
\n objective=<\/span>'multi:softprob'<\/span>,<\/span>
\n random_state=<\/span>13<\/span>,<\/span>
\n enable_categorical=<\/span>True<\/span>,<\/span>
\n tree_method=<\/span>'hist'<\/span>,<\/span>
\n device=<\/span>'cuda'<\/span>
\n )<\/span>
\n elif<\/span> model_type ==<\/span> 'cat'<\/span>:<\/span>
\n model =<\/span> CatBoostClassifier(<\/span>
\n iterations=<\/span>8000<\/span>,<\/span>
\n learning_rate=<\/span>0.03<\/span>,<\/span>
\n depth=<\/span>10<\/span>,<\/span>
\n loss_function=<\/span>'MultiClass'<\/span>,<\/span>
\n eval_metric=<\/span>'MultiClass'<\/span>,<\/span>
\n random_seed=<\/span>42<\/span>,<\/span>
\n od_type=<\/span>'Iter'<\/span>,<\/span>
\n od_wait=<\/span>500<\/span>,<\/span>
\n verbose=<\/span>100<\/span>,<\/span>
\n task_type=<\/span>"GPU"<\/span>
\n )<\/span>
\n elif<\/span> model_type ==<\/span> 'lgb'<\/span>:<\/span>
\n model =<\/span> LGBMClassifier(<\/span>
\n n_estimators=<\/span>8000<\/span>,<\/span>
\n learning_rate=<\/span>0.03<\/span>,<\/span>
\n num_leaves=<\/span>255<\/span>,<\/span>
\n max_depth=<\/span>10<\/span>,<\/span>
\n subsample=<\/span>0.8<\/span>,<\/span>
\n colsample_bytree=<\/span>0.7<\/span>,<\/span>
\n class_weight=<\/span>'balanced'<\/span>,<\/span>
\n metric=<\/span>'multi_logloss'<\/span>,<\/span>
\n early_stopping_rounds=<\/span>500<\/span>,<\/span>
\n random_state=<\/span>42<\/span>,<\/span>
\n verbosity=<\/span>–<\/span>1<\/span>
\n )<\/span><\/p>\n

model.<\/span>fit(<\/span>x_tr,<\/span> y_tr,<\/span> eval_set=<\/span>[<\/span>(<\/span>x_val,<\/span> y_val)<\/span>]<\/span>,<\/span> verbose=<\/span>100<\/span>)<\/span>
\n val_pred =<\/span> model.<\/span>predict(<\/span>x_val)<\/span>
\n score =<\/span> accuracy_score(<\/span>y_val,<\/span> val_pred)<\/span>
\n print<\/span>(<\/span>f"Validation Accuracy: <\/span>{<\/span>score:<\/span>.4f<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

oof_preds[<\/span>val_idx]<\/span> =<\/span> val_pred
\n models.<\/span>append(<\/span>model)<\/span><\/p>\n

scores.<\/span>append(<\/span>score)<\/span><\/p>\n

print<\/span>(<\/span>f"\\\\nAverage CV Accuracy: <\/span>{<\/span>np.<\/span>mean(<\/span>scores)<\/span>:<\/span>.4f<\/span>}<\/span><\/span> \u00b1 <\/span>{<\/span>np.<\/span>std(<\/span>scores)<\/span>:<\/span>.4f<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n return<\/span> models,<\/span> scores<\/p>\n

def<\/span> predict_test<\/span>(<\/span>models,<\/span> X_test)<\/span>:<\/span>
\n """\u5bf9\u6d4b\u8bd5\u96c6\u8fdb\u884c\u9884\u6d4b\u5e76\u53d6\u5e73\u5747"""<\/span>
\n pred_proba =<\/span> np.<\/span>zeros(<\/span>(<\/span>X_test.<\/span>shape[<\/span>0<\/span>]<\/span>,<\/span> len<\/span>(<\/span>np.<\/span>unique(<\/span>Y_train)<\/span>)<\/span>)<\/span>)<\/span>
\n for<\/span> model in<\/span> models:<\/span>
\n pred_proba +=<\/span> model.<\/span>predict_proba(<\/span>X_test)<\/span> \/<\/span> len<\/span>(<\/span>models)<\/span>
\n return<\/span> pred_proba<\/p>\n

def<\/span> generate_submission<\/span>(<\/span>df_test,<\/span> pred_proba,<\/span> le,<\/span> output_path=<\/span>'submission.csv'<\/span>)<\/span>:<\/span>
\n """\u751f\u6210\u63d0\u4ea4\u6587\u4ef6"""<\/span>
\n pred_top3 =<\/span> np.<\/span>argsort(<\/span>pred_proba,<\/span> axis=<\/span>1<\/span>)<\/span>[<\/span>:<\/span>,<\/span> –<\/span>3<\/span>:<\/span>]<\/span>[<\/span>:<\/span>,<\/span> :<\/span>:<\/span>–<\/span>1<\/span>]<\/span>
\n top3_labels =<\/span> [<\/span>list<\/span>(<\/span>le.<\/span>classes_[<\/span>i]<\/span>)<\/span> for<\/span> i in<\/span> pred_top3]<\/span><\/p>\n

submission =<\/span> pd.<\/span>DataFrame(<\/span>{<\/span>
\n 'id'<\/span>:<\/span> df_test[<\/span>'id'<\/span>]<\/span>,<\/span>
\n 'Fertilizer Name'<\/span>:<\/span> [<\/span>' '<\/span>.<\/span>join(<\/span>row)<\/span> for<\/span> row in<\/span> top3_labels]<\/span>
\n }<\/span>)<\/span><\/p>\n

submission.<\/span>to_csv(<\/span>output_path,<\/span> index=<\/span>False<\/span>)<\/span>
\n print<\/span>(<\/span>f"Submission saved to <\/span>{<\/span>output_path}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

if<\/span> __name__ ==<\/span> '__main__'<\/span>:<\/span>
\n init(<\/span>)<\/span><\/p>\n

# Step 1: \u52a0\u8f7d\u6570\u636e<\/span>
\n df_train,<\/span> df_test =<\/span> load_data(<\/span>'train.csv'<\/span>,<\/span> 'test.csv'<\/span>)<\/span><\/p>\n

# Step 2: \u51c6\u5907\u6570\u636e<\/span>
\n X_train,<\/span> Y_train,<\/span> X_test =<\/span> prepare_data(<\/span>df_train,<\/span> df_test)<\/span><\/p>\n

# Step 3: \u8bad\u7ec3\u6a21\u578b（\u652f\u6301 xgb\/cat\/lgb）<\/span>
\n models,<\/span> scores =<\/span> train_model(<\/span>X_train,<\/span> Y_train,<\/span> model_type=<\/span>'xgb'<\/span>,<\/span> n_splits=<\/span>5<\/span>)<\/span><\/p>\n

# Step 4: \u9884\u6d4b\u6d4b\u8bd5\u96c6<\/span>
\n pred_proba =<\/span> predict_test(<\/span>models,<\/span> X_test)<\/span><\/p>\n

# Step 5: \u751f\u6210\u63d0\u4ea4\u6587\u4ef6<\/span>
\n le =<\/span> LabelEncoder(<\/span>)<\/span>
\n le.<\/span>fit(<\/span>df_train[<\/span>'Fertilizer Name'<\/span>]<\/span>)<\/span>
\n generate_submission(<\/span>df_test,<\/span> pred_proba,<\/span> le)<\/span>
\n#AI\u751f\u6210\u7248\u672c0.34190<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb381\u6b21\u30023.\u7531\u4e8elabel\u662fcategory\u7c7b\u578b\uff0c\u4f46\u662fxgb\u4e0d\u53ef\u4ee5\u5904\u7406category\u7c7b\u578b\uff0c\u56e0\u6b64\u9700\u8981\u5148\u7f16\u7801\uff0c\u6700\u540e\u6c42\u51fa\u7ed3\u679c\u4e4b\u540e\u518d\u89e3\u7801\u30021.\u6709\u6570\u5b57\u578b\u548c\u7c7b\u522b\u578b\uff0c\u7c7b\u522b\u4e0d\u80fd\u968f\u610f\u6362\u6210\u6570\u5b57\uff0c\u72ec\u70ed\u7f16\u7801\u3002cat\u53ef\u4ee5\u76f4\u63a5\u5904\u7406category\u7c7b\u578b\u30021.catboost\u4ea4\u53c9\u9a8c\u8bc1\u3001xgboost\u4ea4\u53c9\u9a8c\u8bc1\u3002\u7ed9\u51fa\u571f\u58e4\u7684\u7279\u6027\uff0c\u9884\u6d4b\u51fa3\u79cd\u6700\u4f73\u7684\u80a5\u6599\u30022.\u6784\u9020\u4e00\u4e9b\u76f8\u5173\u571f\u58e4\u7279\u6027\u7279\u5f81\u3002<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[50,2395,62],"topic":[],"class_list":["post-42202","post","type-post","status-publish","format-standard","hentry","category-server","tag-50","tag-2395","tag-62"],"yoast_head":"\nKaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/42202.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb381\u6b21\u30023.\u7531\u4e8elabel\u662fcategory\u7c7b\u578b\uff0c\u4f46\u662fxgb\u4e0d\u53ef\u4ee5\u5904\u7406category\u7c7b\u578b\uff0c\u56e0\u6b64\u9700\u8981\u5148\u7f16\u7801\uff0c\u6700\u540e\u6c42\u51fa\u7ed3\u679c\u4e4b\u540e\u518d\u89e3\u7801\u30021.\u6709\u6570\u5b57\u578b\u548c\u7c7b\u522b\u578b\uff0c\u7c7b\u522b\u4e0d\u80fd\u968f\u610f\u6362\u6210\u6570\u5b57\uff0c\u72ec\u70ed\u7f16\u7801\u3002cat\u53ef\u4ee5\u76f4\u63a5\u5904\u7406category\u7c7b\u578b\u30021.catboost\u4ea4\u53c9\u9a8c\u8bc1\u3001xgboost\u4ea4\u53c9\u9a8c\u8bc1\u3002\u7ed9\u51fa\u571f\u58e4\u7684\u7279\u6027\uff0c\u9884\u6d4b\u51fa3\u79cd\u6700\u4f73\u7684\u80a5\u6599\u30022.\u6784\u9020\u4e00\u4e9b\u76f8\u5173\u571f\u58e4\u7279\u6027\u7279\u5f81\u3002\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/42202.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2025-06-06T10:26:01+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/42202.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/42202.html\",\"name\":\"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2025-06-06T10:26:01+00:00\",\"dateModified\":\"2025-06-06T10:26:01+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/42202.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/42202.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/42202.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost)\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/42202.html","og_locale":"zh_CN","og_type":"article","og_title":"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb381\u6b21\u30023.\u7531\u4e8elabel\u662fcategory\u7c7b\u578b\uff0c\u4f46\u662fxgb\u4e0d\u53ef\u4ee5\u5904\u7406category\u7c7b\u578b\uff0c\u56e0\u6b64\u9700\u8981\u5148\u7f16\u7801\uff0c\u6700\u540e\u6c42\u51fa\u7ed3\u679c\u4e4b\u540e\u518d\u89e3\u7801\u30021.\u6709\u6570\u5b57\u578b\u548c\u7c7b\u522b\u578b\uff0c\u7c7b\u522b\u4e0d\u80fd\u968f\u610f\u6362\u6210\u6570\u5b57\uff0c\u72ec\u70ed\u7f16\u7801\u3002cat\u53ef\u4ee5\u76f4\u63a5\u5904\u7406category\u7c7b\u578b\u30021.catboost\u4ea4\u53c9\u9a8c\u8bc1\u3001xgboost\u4ea4\u53c9\u9a8c\u8bc1\u3002\u7ed9\u51fa\u571f\u58e4\u7684\u7279\u6027\uff0c\u9884\u6d4b\u51fa3\u79cd\u6700\u4f73\u7684\u80a5\u6599\u30022.\u6784\u9020\u4e00\u4e9b\u76f8\u5173\u571f\u58e4\u7279\u6027\u7279\u5f81\u3002","og_url":"https:\/\/www.wsisp.com\/helps\/42202.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2025-06-06T10:26:01+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"3 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/42202.html","url":"https:\/\/www.wsisp.com\/helps\/42202.html","name":"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2025-06-06T10:26:01+00:00","dateModified":"2025-06-06T10:26:01+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/42202.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/42202.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/42202.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"Kaggle-Predicting Optimal Fertilizers-(\u591a\u5206\u7c7b+xgboost)"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/42202","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=42202"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/42202\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=42202"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=42202"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=42202"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=42202"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}