|
4 | 4 | "cell_type": "markdown",
|
5 | 5 | "metadata": {
|
6 | 6 | "application/vnd.databricks.v1+cell": {
|
7 |
| - "cellMetadata": {}, |
| 7 | + "cellMetadata": { |
| 8 | + "byteLimit": 2048000, |
| 9 | + "rowLimit": 10000 |
| 10 | + }, |
8 | 11 | "inputWidgets": {},
|
9 | 12 | "nuid": "a23f6d56-6d8d-44bc-b796-cedda9e17c21",
|
10 | 13 | "showTitle": false,
|
|
21 | 24 | "execution_count": 0,
|
22 | 25 | "metadata": {
|
23 | 26 | "application/vnd.databricks.v1+cell": {
|
24 |
| - "cellMetadata": {}, |
| 27 | + "cellMetadata": { |
| 28 | + "byteLimit": 2048000, |
| 29 | + "rowLimit": 10000 |
| 30 | + }, |
25 | 31 | "inputWidgets": {},
|
26 | 32 | "nuid": "0a69d78b-43d7-4f9e-a05d-026985c2539f",
|
27 | 33 | "showTitle": false,
|
|
40 | 46 | "cell_type": "markdown",
|
41 | 47 | "metadata": {
|
42 | 48 | "application/vnd.databricks.v1+cell": {
|
43 |
| - "cellMetadata": {}, |
| 49 | + "cellMetadata": { |
| 50 | + "byteLimit": 2048000, |
| 51 | + "rowLimit": 10000 |
| 52 | + }, |
44 | 53 | "inputWidgets": {},
|
45 | 54 | "nuid": "2a54b88b-06bd-43e4-978a-c0c5d33ca5bb",
|
46 | 55 | "showTitle": false,
|
|
122 | 131 | "execution_count": 0,
|
123 | 132 | "metadata": {
|
124 | 133 | "application/vnd.databricks.v1+cell": {
|
125 |
| - "cellMetadata": {}, |
| 134 | + "cellMetadata": { |
| 135 | + "byteLimit": 2048000, |
| 136 | + "rowLimit": 10000 |
| 137 | + }, |
126 | 138 | "inputWidgets": {},
|
127 | 139 | "nuid": "c260f510-542b-4067-a6f4-ffed86995056",
|
128 | 140 | "showTitle": false,
|
129 | 141 | "tableResultSettingsMap": {},
|
130 | 142 | "title": ""
|
131 | 143 | }
|
132 | 144 | },
|
133 |
| - "outputs": [], |
| 145 | + "outputs": [ |
| 146 | + { |
| 147 | + "output_type": "stream", |
| 148 | + "name": "stdout", |
| 149 | + "output_type": "stream", |
| 150 | + "text": [ |
| 151 | + "+------+------------+\n|bus_id|arrival_time|\n+------+------------+\n| 1| 2|\n| 2| 4|\n| 3| 7|\n+------+------------+\n\n+------------+------------+\n|passenger_id|arrival_time|\n+------------+------------+\n| 11| 1|\n| 12| 5|\n| 13| 6|\n| 14| 7|\n+------------+------------+\n\n" |
| 152 | + ] |
| 153 | + } |
| 154 | + ], |
134 | 155 | "source": [
|
135 | 156 | "buses_data_2142 = [\n",
|
136 | 157 | " (1, 2),\n",
|
|
153 | 174 | "passengers_df_2142 = spark.createDataFrame(passengers_data_2142, passengers_columns_2142)\n",
|
154 | 175 | "passengers_df_2142.show()"
|
155 | 176 | ]
|
| 177 | + }, |
| 178 | + { |
| 179 | + "cell_type": "code", |
| 180 | + "execution_count": 0, |
| 181 | + "metadata": { |
| 182 | + "application/vnd.databricks.v1+cell": { |
| 183 | + "cellMetadata": { |
| 184 | + "byteLimit": 2048000, |
| 185 | + "rowLimit": 10000 |
| 186 | + }, |
| 187 | + "inputWidgets": {}, |
| 188 | + "nuid": "afaca1d0-79e0-4ffc-9c77-79c6fc7e38f4", |
| 189 | + "showTitle": false, |
| 190 | + "tableResultSettingsMap": {}, |
| 191 | + "title": "" |
| 192 | + } |
| 193 | + }, |
| 194 | + "outputs": [], |
| 195 | + "source": [ |
| 196 | + "joined_df_2142 = passengers_df_2142.alias(\"p\")\\\n", |
| 197 | + " .join( buses_df_2142.alias(\"b\"), col(\"p.arrival_time\") <= col(\"b.arrival_time\"))" |
| 198 | + ] |
| 199 | + }, |
| 200 | + { |
| 201 | + "cell_type": "code", |
| 202 | + "execution_count": 0, |
| 203 | + "metadata": { |
| 204 | + "application/vnd.databricks.v1+cell": { |
| 205 | + "cellMetadata": { |
| 206 | + "byteLimit": 2048000, |
| 207 | + "rowLimit": 10000 |
| 208 | + }, |
| 209 | + "inputWidgets": {}, |
| 210 | + "nuid": "25a51bb8-bf85-4f6b-b942-84c2d4dbc22d", |
| 211 | + "showTitle": false, |
| 212 | + "tableResultSettingsMap": {}, |
| 213 | + "title": "" |
| 214 | + } |
| 215 | + }, |
| 216 | + "outputs": [], |
| 217 | + "source": [ |
| 218 | + "windowSpec = Window.partitionBy(\"p.passenger_id\")" |
| 219 | + ] |
| 220 | + }, |
| 221 | + { |
| 222 | + "cell_type": "code", |
| 223 | + "execution_count": 0, |
| 224 | + "metadata": { |
| 225 | + "application/vnd.databricks.v1+cell": { |
| 226 | + "cellMetadata": { |
| 227 | + "byteLimit": 2048000, |
| 228 | + "rowLimit": 10000 |
| 229 | + }, |
| 230 | + "inputWidgets": {}, |
| 231 | + "nuid": "9dfccb64-9516-4036-afce-8b228a9a05e6", |
| 232 | + "showTitle": false, |
| 233 | + "tableResultSettingsMap": {}, |
| 234 | + "title": "" |
| 235 | + } |
| 236 | + }, |
| 237 | + "outputs": [], |
| 238 | + "source": [ |
| 239 | + "passenger_bus_df_2142 = joined_df_2142\\\n", |
| 240 | + " .withColumn( \"min_bus_time\", min(\"b.arrival_time\").over(windowSpec))\\\n", |
| 241 | + " .where(col(\"b.arrival_time\") == col(\"min_bus_time\")) \\\n", |
| 242 | + " .select(\"p.passenger_id\", \"b.bus_id\")" |
| 243 | + ] |
| 244 | + }, |
| 245 | + { |
| 246 | + "cell_type": "code", |
| 247 | + "execution_count": 0, |
| 248 | + "metadata": { |
| 249 | + "application/vnd.databricks.v1+cell": { |
| 250 | + "cellMetadata": { |
| 251 | + "byteLimit": 2048000, |
| 252 | + "rowLimit": 10000 |
| 253 | + }, |
| 254 | + "inputWidgets": {}, |
| 255 | + "nuid": "45a272fb-7400-4f5a-acc5-43e18e8745fc", |
| 256 | + "showTitle": false, |
| 257 | + "tableResultSettingsMap": {}, |
| 258 | + "title": "" |
| 259 | + } |
| 260 | + }, |
| 261 | + "outputs": [], |
| 262 | + "source": [ |
| 263 | + "bus_counts_df_2142 = passenger_bus_df_2142\\\n", |
| 264 | + " .groupBy(\"bus_id\")\\\n", |
| 265 | + " .agg(count(\"passenger_id\").alias(\"passengers_cnt\")\n", |
| 266 | + " )" |
| 267 | + ] |
| 268 | + }, |
| 269 | + { |
| 270 | + "cell_type": "code", |
| 271 | + "execution_count": 0, |
| 272 | + "metadata": { |
| 273 | + "application/vnd.databricks.v1+cell": { |
| 274 | + "cellMetadata": { |
| 275 | + "byteLimit": 2048000, |
| 276 | + "rowLimit": 10000 |
| 277 | + }, |
| 278 | + "inputWidgets": {}, |
| 279 | + "nuid": "860f8f74-09f1-4067-8df0-45d9fcf6c3b5", |
| 280 | + "showTitle": false, |
| 281 | + "tableResultSettingsMap": {}, |
| 282 | + "title": "" |
| 283 | + } |
| 284 | + }, |
| 285 | + "outputs": [ |
| 286 | + { |
| 287 | + "output_type": "stream", |
| 288 | + "name": "stdout", |
| 289 | + "output_type": "stream", |
| 290 | + "text": [ |
| 291 | + "+------+--------------+\n|bus_id|passengers_cnt|\n+------+--------------+\n| 1| 1|\n| 2| 0|\n| 3| 3|\n+------+--------------+\n\n" |
| 292 | + ] |
| 293 | + } |
| 294 | + ], |
| 295 | + "source": [ |
| 296 | + "buses_df_2142\\\n", |
| 297 | + " .join(bus_counts_df_2142, \"bus_id\", \"left\").fillna(0).orderBy(\"bus_id\")\\\n", |
| 298 | + " .select('bus_id','passengers_cnt').show()" |
| 299 | + ] |
156 | 300 | }
|
157 | 301 | ],
|
158 | 302 | "metadata": {
|
159 | 303 | "application/vnd.databricks.v1+notebook": {
|
160 |
| - "computePreferences": null, |
| 304 | + "computePreferences": { |
| 305 | + "hardware": { |
| 306 | + "accelerator": null, |
| 307 | + "gpuPoolId": null, |
| 308 | + "memory": null |
| 309 | + } |
| 310 | + }, |
161 | 311 | "dashboards": [],
|
162 | 312 | "environmentMetadata": {
|
163 | 313 | "base_environment": "",
|
164 |
| - "environment_version": "1" |
| 314 | + "environment_version": "2" |
165 | 315 | },
|
166 | 316 | "inputWidgetPreferences": null,
|
167 | 317 | "language": "python",
|
|
0 commit comments