{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "c6e41d140bb8f818", "metadata": { "collapsed": false }, "outputs": [], "source": [ "# 一、选择特征" ] }, { "cell_type": "code", "execution_count": 2, "id": "063d5686-3a6b-4879-ba01-32d6674528d8", "metadata": { "ExecuteTime": { "end_time": "2024-09-27T01:56:56.843195Z", "start_time": "2024-09-27T01:56:56.577410Z" }, "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", " | \n", " | 地区生产总值(亿元) | \n", "第一产业占比 | \n", "第二产业占比 | \n", "第三产业占比 | \n", "人均地区生产总值(按常住人口)(万元) | \n", "人均地区生产总值(按户籍人口)(万元) | \n", "地方一般公共预算收入(亿元) | \n", "地方一般公共预算支出(亿元) | \n", "教育支出(亿元) | \n", "科学技术支出(亿元) | \n", "... | \n", "住宅销售面积(万平方米)\\n实际为房地产销售面积 | \n", "社会消费品零售总额(亿元) | \n", "当年实际使用外资金额(亿美元) | \n", "空气质量达标天数\\n空气优良天数 | \n", "规模以上工业企业数 | \n", "规模以上工业企业总产值 | \n", "工业用地(万元/㎡) | \n", "商服用地(万元/㎡) | \n", "住宅用地(万元/㎡) | \n", "其他用地(万元/㎡) | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
城市 | \n", "年度 | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
杭州市上城区 | \n", "2023 | \n", "2668.48 | \n", "0.0 | \n", "23.3 | \n", "76.7 | \n", "19.329800 | \n", "29.548001 | \n", "244.94 | \n", "155.32 | \n", "43.800240 | \n", "13.6300 | \n", "... | \n", "175.70 | \n", "1106.9500 | \n", "11.9300 | \n", "310.6150 | \n", "NaN | \n", "NaN | \n", "0.13 | \n", "3.73 | \n", "6.57 | \n", "0.91 | \n", "
2022 | \n", "2560.53 | \n", "0.0 | \n", "26.2 | \n", "73.8 | \n", "18.924800 | \n", "29.004644 | \n", "210.56 | \n", "152.21 | \n", "37.900290 | \n", "11.8500 | \n", "... | \n", "186.37 | \n", "1073.0900 | \n", "10.9000 | \n", "295.0000 | \n", "94.0 | \n", "1001.1883 | \n", "0.13 | \n", "3.73 | \n", "6.57 | \n", "0.91 | \n", "|
杭州市拱墅区 | \n", "2023 | \n", "2091.50 | \n", "0.0 | \n", "9.2 | \n", "90.8 | \n", "17.690000 | \n", "23.376551 | \n", "199.18 | \n", "132.23 | \n", "35.700000 | \n", "9.3300 | \n", "... | \n", "189.30 | \n", "1363.9000 | \n", "7.4500 | \n", "308.0000 | \n", "NaN | \n", "NaN | \n", "0.27 | \n", "1.72 | \n", "5.40 | \n", "0.00 | \n", "
2022 | \n", "2000.10 | \n", "0.0 | \n", "9.7 | \n", "90.3 | \n", "16.993203 | \n", "22.564305 | \n", "184.29 | \n", "134.20 | \n", "33.170000 | \n", "8.1000 | \n", "... | \n", "180.00 | \n", "1312.9000 | \n", "2.7100 | \n", "304.0000 | \n", "97.0 | \n", "299.4529 | \n", "0.11 | \n", "1.97 | \n", "5.48 | \n", "0.00 | \n", "|
杭州市西湖区 | \n", "2023 | \n", "2087.40 | \n", "0.2 | \n", "6.9 | \n", "92.9 | \n", "17.860000 | \n", "25.580882 | \n", "233.80 | \n", "169.30 | \n", "57.400000 | \n", "NaN | \n", "... | \n", "119.40 | \n", "906.3000 | \n", "4.0000 | \n", "308.0000 | \n", "NaN | \n", "343.2000 | \n", "0.14 | \n", "1.45 | \n", "3.10 | \n", "0.00 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
温州市苍南县 | \n", "2022 | \n", "427.56 | \n", "7.3 | \n", "38.1 | \n", "54.6 | \n", "5.050900 | \n", "4.477068 | \n", "30.27 | \n", "89.32 | \n", "20.313100 | \n", "1.2236 | \n", "... | \n", "40.96 | \n", "53.8157 | \n", "53.0676 | \n", "0.5168 | \n", "237400.0 | \n", "442.0000 | \n", "0.09 | \n", "0.26 | \n", "1.21 | \n", "0.23 | \n", "
温州市文成县 | \n", "2023 | \n", "136.81 | \n", "7.8 | \n", "24.7 | \n", "67.5 | \n", "4.682067 | \n", "3.398162 | \n", "11.47 | \n", "53.98 | \n", "9.107921 | \n", "0.8450 | \n", "... | \n", "12.03 | \n", "9.3100 | \n", "NaN | \n", "NaN | \n", "22200.0 | \n", "NaN | \n", "0.03 | \n", "0.00 | \n", "0.00 | \n", "0.04 | \n", "
2022 | \n", "126.55 | \n", "8.5 | \n", "25.8 | \n", "65.7 | \n", "4.359283 | \n", "3.132426 | \n", "10.77 | \n", "50.59 | \n", "8.670000 | \n", "0.7345 | \n", "... | \n", "10.46 | \n", "5.4100 | \n", "5.5681 | \n", "0.1731 | \n", "19700.0 | \n", "60.0000 | \n", "0.03 | \n", "0.00 | \n", "0.75 | \n", "0.12 | \n", "|
温州市泰顺县 | \n", "2023 | \n", "157.60 | \n", "7.0 | \n", "38.1 | \n", "54.9 | \n", "5.869500 | \n", "4.314262 | \n", "16.02 | \n", "61.57 | \n", "8.110000 | \n", "0.5554 | \n", "... | \n", "12.25 | \n", "11.8800 | \n", "NaN | \n", "NaN | \n", "28200.0 | \n", "55.0000 | \n", "0.05 | \n", "0.06 | \n", "0.58 | \n", "0.04 | \n", "
2022 | \n", "143.98 | \n", "7.8 | \n", "36.3 | \n", "55.8 | \n", "5.392700 | \n", "3.913563 | \n", "15.10 | \n", "59.73 | \n", "7.958200 | \n", "0.4827 | \n", "... | \n", "19.31 | \n", "13.7600 | \n", "14.6979 | \n", "0.0290 | \n", "24800.0 | \n", "56.0000 | \n", "0.04 | \n", "0.13 | \n", "0.74 | \n", "0.06 | \n", "
64 rows × 25 columns
\n", "XGBRegressor(base_score=None, booster=None, callbacks=None,\n", " colsample_bylevel=None, colsample_bynode=None,\n", " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", " enable_categorical=False, eval_metric=None, feature_types=None,\n", " gamma=None, grow_policy=None, importance_type=None,\n", " interaction_constraints=None, learning_rate=None, max_bin=None,\n", " max_cat_threshold=None, max_cat_to_onehot=None,\n", " max_delta_step=None, max_depth=None, max_leaves=None,\n", " min_child_weight=None, missing=nan, monotone_constraints=None,\n", " multi_strategy=None, n_estimators=None, n_jobs=None,\n", " num_parallel_tree=None, random_state=None, ...)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
XGBRegressor(base_score=None, booster=None, callbacks=None,\n", " colsample_bylevel=None, colsample_bynode=None,\n", " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", " enable_categorical=False, eval_metric=None, feature_types=None,\n", " gamma=None, grow_policy=None, importance_type=None,\n", " interaction_constraints=None, learning_rate=None, max_bin=None,\n", " max_cat_threshold=None, max_cat_to_onehot=None,\n", " max_delta_step=None, max_depth=None, max_leaves=None,\n", " min_child_weight=None, missing=nan, monotone_constraints=None,\n", " multi_strategy=None, n_estimators=None, n_jobs=None,\n", " num_parallel_tree=None, random_state=None, ...)
XGBRegressor(base_score=None, booster='gbtree', callbacks=None,\n", " colsample_bylevel=None, colsample_bynode=None,\n", " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", " enable_categorical=False, eval_metric=None, feature_types=None,\n", " gamma=None, grow_policy=None, importance_type=None,\n", " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n", " max_cat_threshold=None, max_cat_to_onehot=None,\n", " max_delta_step=None, max_depth=None, max_leaves=None,\n", " min_child_weight=None, missing=nan, monotone_constraints=None,\n", " multi_strategy=None, n_estimators=75, n_jobs=None,\n", " num_parallel_tree=None, random_state=None, ...)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
XGBRegressor(base_score=None, booster='gbtree', callbacks=None,\n", " colsample_bylevel=None, colsample_bynode=None,\n", " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", " enable_categorical=False, eval_metric=None, feature_types=None,\n", " gamma=None, grow_policy=None, importance_type=None,\n", " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n", " max_cat_threshold=None, max_cat_to_onehot=None,\n", " max_delta_step=None, max_depth=None, max_leaves=None,\n", " min_child_weight=None, missing=nan, monotone_constraints=None,\n", " multi_strategy=None, n_estimators=75, n_jobs=None,\n", " num_parallel_tree=None, random_state=None, ...)