|
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": "24f8e8c0-d56b-4821-a900-bbe934dce4d7",
|
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": "243b190c-af0b-4bd1-9507-8e2be2fceca3",
|
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": "2d9dc49c-3f2c-4ff6-8e98-5e72a86b1bac",
|
46 | 55 | "showTitle": false,
|
|
119 | 128 | "execution_count": 0,
|
120 | 129 | "metadata": {
|
121 | 130 | "application/vnd.databricks.v1+cell": {
|
122 |
| - "cellMetadata": {}, |
| 131 | + "cellMetadata": { |
| 132 | + "byteLimit": 2048000, |
| 133 | + "rowLimit": 10000 |
| 134 | + }, |
123 | 135 | "inputWidgets": {},
|
124 | 136 | "nuid": "5d66d20c-58e2-4ee9-8356-d736216372c3",
|
125 | 137 | "showTitle": false,
|
126 | 138 | "tableResultSettingsMap": {},
|
127 | 139 | "title": ""
|
128 | 140 | }
|
129 | 141 | },
|
130 |
| - "outputs": [], |
| 142 | + "outputs": [ |
| 143 | + { |
| 144 | + "output_type": "stream", |
| 145 | + "name": "stdout", |
| 146 | + "output_type": "stream", |
| 147 | + "text": [ |
| 148 | + "+---+--------+\n| id| name|\n+---+--------+\n| 1| Winston|\n| 7|Jonathan|\n+---+--------+\n\n+---+----------+\n| id|login_date|\n+---+----------+\n| 7|2020-05-30|\n| 1|2020-05-30|\n| 7|2020-05-31|\n| 7|2020-06-01|\n| 7|2020-06-02|\n| 7|2020-06-02|\n| 7|2020-06-03|\n| 1|2020-06-07|\n| 7|2020-06-10|\n+---+----------+\n\n" |
| 149 | + ] |
| 150 | + } |
| 151 | + ], |
131 | 152 | "source": [
|
132 | 153 | "accounts_data_1454 = [\n",
|
133 | 154 | " (1, \"Winston\"),\n",
|
|
154 | 175 | "logins_df_1454 = spark.createDataFrame(logins_data_1454, logins_columns_1454)\n",
|
155 | 176 | "logins_df_1454.show()"
|
156 | 177 | ]
|
| 178 | + }, |
| 179 | + { |
| 180 | + "cell_type": "code", |
| 181 | + "execution_count": 0, |
| 182 | + "metadata": { |
| 183 | + "application/vnd.databricks.v1+cell": { |
| 184 | + "cellMetadata": { |
| 185 | + "byteLimit": 2048000, |
| 186 | + "rowLimit": 10000 |
| 187 | + }, |
| 188 | + "inputWidgets": {}, |
| 189 | + "nuid": "61e43104-e7f2-478a-bcb0-d03828987e08", |
| 190 | + "showTitle": false, |
| 191 | + "tableResultSettingsMap": {}, |
| 192 | + "title": "" |
| 193 | + } |
| 194 | + }, |
| 195 | + "outputs": [], |
| 196 | + "source": [ |
| 197 | + "logins_df_1454 = logins_df_1454\\\n", |
| 198 | + " .withColumn(\"login_date\", to_date(\"login_date\"))" |
| 199 | + ] |
| 200 | + }, |
| 201 | + { |
| 202 | + "cell_type": "code", |
| 203 | + "execution_count": 0, |
| 204 | + "metadata": { |
| 205 | + "application/vnd.databricks.v1+cell": { |
| 206 | + "cellMetadata": { |
| 207 | + "byteLimit": 2048000, |
| 208 | + "rowLimit": 10000 |
| 209 | + }, |
| 210 | + "inputWidgets": {}, |
| 211 | + "nuid": "9d34d2c0-23ef-4484-ae33-7c78db84d4be", |
| 212 | + "showTitle": false, |
| 213 | + "tableResultSettingsMap": {}, |
| 214 | + "title": "" |
| 215 | + } |
| 216 | + }, |
| 217 | + "outputs": [], |
| 218 | + "source": [ |
| 219 | + "n = 5" |
| 220 | + ] |
| 221 | + }, |
| 222 | + { |
| 223 | + "cell_type": "code", |
| 224 | + "execution_count": 0, |
| 225 | + "metadata": { |
| 226 | + "application/vnd.databricks.v1+cell": { |
| 227 | + "cellMetadata": { |
| 228 | + "byteLimit": 2048000, |
| 229 | + "rowLimit": 10000 |
| 230 | + }, |
| 231 | + "inputWidgets": {}, |
| 232 | + "nuid": "069478cc-d700-46d5-a3f9-b98df6b595b5", |
| 233 | + "showTitle": false, |
| 234 | + "tableResultSettingsMap": {}, |
| 235 | + "title": "" |
| 236 | + } |
| 237 | + }, |
| 238 | + "outputs": [], |
| 239 | + "source": [ |
| 240 | + "logins_df_1454 = logins_df_1454.dropDuplicates([\"id\", \"login_date\"])" |
| 241 | + ] |
| 242 | + }, |
| 243 | + { |
| 244 | + "cell_type": "code", |
| 245 | + "execution_count": 0, |
| 246 | + "metadata": { |
| 247 | + "application/vnd.databricks.v1+cell": { |
| 248 | + "cellMetadata": { |
| 249 | + "byteLimit": 2048000, |
| 250 | + "rowLimit": 10000 |
| 251 | + }, |
| 252 | + "inputWidgets": {}, |
| 253 | + "nuid": "2880faa5-14e9-486a-9243-9e8998a604c2", |
| 254 | + "showTitle": false, |
| 255 | + "tableResultSettingsMap": {}, |
| 256 | + "title": "" |
| 257 | + } |
| 258 | + }, |
| 259 | + "outputs": [], |
| 260 | + "source": [ |
| 261 | + "windowSpec = Window.partitionBy(\"id\").orderBy(\"login_date\")" |
| 262 | + ] |
| 263 | + }, |
| 264 | + { |
| 265 | + "cell_type": "code", |
| 266 | + "execution_count": 0, |
| 267 | + "metadata": { |
| 268 | + "application/vnd.databricks.v1+cell": { |
| 269 | + "cellMetadata": { |
| 270 | + "byteLimit": 2048000, |
| 271 | + "rowLimit": 10000 |
| 272 | + }, |
| 273 | + "inputWidgets": {}, |
| 274 | + "nuid": "245f6ff2-793d-46c8-8324-c5c339f44a74", |
| 275 | + "showTitle": false, |
| 276 | + "tableResultSettingsMap": {}, |
| 277 | + "title": "" |
| 278 | + } |
| 279 | + }, |
| 280 | + "outputs": [], |
| 281 | + "source": [ |
| 282 | + "logins_df_1454 = logins_df_1454\\\n", |
| 283 | + " .withColumn(\"grp\", \n", |
| 284 | + " datediff(\"login_date\", lag(\"login_date\", 1).over(windowSpec))\n", |
| 285 | + " )\\\n", |
| 286 | + " .withColumn(\"grp\", when(col(\"grp\").isNull() | (col(\"grp\") != 1), 0).otherwise(1)\n", |
| 287 | + " )\\\n", |
| 288 | + " .withColumn(\"streak_grp\", sum(when(col(\"grp\") == 0, 1).otherwise(0)).over(windowSpec))\n" |
| 289 | + ] |
| 290 | + }, |
| 291 | + { |
| 292 | + "cell_type": "code", |
| 293 | + "execution_count": 0, |
| 294 | + "metadata": { |
| 295 | + "application/vnd.databricks.v1+cell": { |
| 296 | + "cellMetadata": { |
| 297 | + "byteLimit": 2048000, |
| 298 | + "rowLimit": 10000 |
| 299 | + }, |
| 300 | + "inputWidgets": {}, |
| 301 | + "nuid": "953ecab5-5c28-4956-a835-e2b6c7a033ab", |
| 302 | + "showTitle": false, |
| 303 | + "tableResultSettingsMap": {}, |
| 304 | + "title": "" |
| 305 | + } |
| 306 | + }, |
| 307 | + "outputs": [], |
| 308 | + "source": [ |
| 309 | + "streak_counts_1454 = logins_df_1454\\\n", |
| 310 | + " .groupBy(\"id\", \"streak_grp\").agg(count(\"*\").alias(\"streak_days\")\n", |
| 311 | + " )" |
| 312 | + ] |
| 313 | + }, |
| 314 | + { |
| 315 | + "cell_type": "code", |
| 316 | + "execution_count": 0, |
| 317 | + "metadata": { |
| 318 | + "application/vnd.databricks.v1+cell": { |
| 319 | + "cellMetadata": { |
| 320 | + "byteLimit": 2048000, |
| 321 | + "rowLimit": 10000 |
| 322 | + }, |
| 323 | + "inputWidgets": {}, |
| 324 | + "nuid": "03857c59-e667-4aa5-956e-768fcb3de627", |
| 325 | + "showTitle": false, |
| 326 | + "tableResultSettingsMap": {}, |
| 327 | + "title": "" |
| 328 | + } |
| 329 | + }, |
| 330 | + "outputs": [], |
| 331 | + "source": [ |
| 332 | + "active_users_df_1454 = streak_counts_1454\\\n", |
| 333 | + " .filter(col(\"streak_days\") >= n)\\\n", |
| 334 | + " .select(\"id\").distinct()" |
| 335 | + ] |
| 336 | + }, |
| 337 | + { |
| 338 | + "cell_type": "code", |
| 339 | + "execution_count": 0, |
| 340 | + "metadata": { |
| 341 | + "application/vnd.databricks.v1+cell": { |
| 342 | + "cellMetadata": { |
| 343 | + "byteLimit": 2048000, |
| 344 | + "rowLimit": 10000 |
| 345 | + }, |
| 346 | + "inputWidgets": {}, |
| 347 | + "nuid": "39f7fb38-ef7d-49fc-878d-ecfdd1e96972", |
| 348 | + "showTitle": false, |
| 349 | + "tableResultSettingsMap": {}, |
| 350 | + "title": "" |
| 351 | + } |
| 352 | + }, |
| 353 | + "outputs": [ |
| 354 | + { |
| 355 | + "output_type": "stream", |
| 356 | + "name": "stdout", |
| 357 | + "output_type": "stream", |
| 358 | + "text": [ |
| 359 | + "+---+--------+\n| id| name|\n+---+--------+\n| 7|Jonathan|\n+---+--------+\n\n" |
| 360 | + ] |
| 361 | + } |
| 362 | + ], |
| 363 | + "source": [ |
| 364 | + "active_users_df_1454\\\n", |
| 365 | + " .join(accounts_df_1454, \"id\").orderBy(\"id\").show()" |
| 366 | + ] |
157 | 367 | }
|
158 | 368 | ],
|
159 | 369 | "metadata": {
|
160 | 370 | "application/vnd.databricks.v1+notebook": {
|
161 |
| - "computePreferences": null, |
| 371 | + "computePreferences": { |
| 372 | + "hardware": { |
| 373 | + "accelerator": null, |
| 374 | + "gpuPoolId": null, |
| 375 | + "memory": null |
| 376 | + } |
| 377 | + }, |
162 | 378 | "dashboards": [],
|
163 | 379 | "environmentMetadata": {
|
164 | 380 | "base_environment": "",
|
165 |
| - "environment_version": "1" |
| 381 | + "environment_version": "2" |
166 | 382 | },
|
167 | 383 | "inputWidgetPreferences": null,
|
168 | 384 | "language": "python",
|
|
0 commit comments