File size: 15,957 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Spark Dataframe Agent\n",
    "\n",
    "This notebook shows how to use agents to interact with a Spark dataframe and Spark Connect. It is mostly optimized for question answering.\n",
    "\n",
    "**NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import create_spark_dataframe_agent\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"...input your openai api key here...\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
      "|PassengerId|Survived|Pclass|                Name|   Sex| Age|SibSp|Parch|          Ticket|   Fare|Cabin|Embarked|\n",
      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
      "|          1|       0|     3|Braund, Mr. Owen ...|  male|22.0|    1|    0|       A/5 21171|   7.25| null|       S|\n",
      "|          2|       1|     1|Cumings, Mrs. Joh...|female|38.0|    1|    0|        PC 17599|71.2833|  C85|       C|\n",
      "|          3|       1|     3|Heikkinen, Miss. ...|female|26.0|    0|    0|STON/O2. 3101282|  7.925| null|       S|\n",
      "|          4|       1|     1|Futrelle, Mrs. Ja...|female|35.0|    1|    0|          113803|   53.1| C123|       S|\n",
      "|          5|       0|     3|Allen, Mr. Willia...|  male|35.0|    0|    0|          373450|   8.05| null|       S|\n",
      "|          6|       0|     3|    Moran, Mr. James|  male|null|    0|    0|          330877| 8.4583| null|       Q|\n",
      "|          7|       0|     1|McCarthy, Mr. Tim...|  male|54.0|    0|    0|           17463|51.8625|  E46|       S|\n",
      "|          8|       0|     3|Palsson, Master. ...|  male| 2.0|    3|    1|          349909| 21.075| null|       S|\n",
      "|          9|       1|     3|Johnson, Mrs. Osc...|female|27.0|    0|    2|          347742|11.1333| null|       S|\n",
      "|         10|       1|     2|Nasser, Mrs. Nich...|female|14.0|    1|    0|          237736|30.0708| null|       C|\n",
      "|         11|       1|     3|Sandstrom, Miss. ...|female| 4.0|    1|    1|         PP 9549|   16.7|   G6|       S|\n",
      "|         12|       1|     1|Bonnell, Miss. El...|female|58.0|    0|    0|          113783|  26.55| C103|       S|\n",
      "|         13|       0|     3|Saundercock, Mr. ...|  male|20.0|    0|    0|       A/5. 2151|   8.05| null|       S|\n",
      "|         14|       0|     3|Andersson, Mr. An...|  male|39.0|    1|    5|          347082| 31.275| null|       S|\n",
      "|         15|       0|     3|Vestrom, Miss. Hu...|female|14.0|    0|    0|          350406| 7.8542| null|       S|\n",
      "|         16|       1|     2|Hewlett, Mrs. (Ma...|female|55.0|    0|    0|          248706|   16.0| null|       S|\n",
      "|         17|       0|     3|Rice, Master. Eugene|  male| 2.0|    4|    1|          382652| 29.125| null|       Q|\n",
      "|         18|       1|     2|Williams, Mr. Cha...|  male|null|    0|    0|          244373|   13.0| null|       S|\n",
      "|         19|       0|     3|Vander Planke, Mr...|female|31.0|    1|    0|          345763|   18.0| null|       S|\n",
      "|         20|       1|     3|Masselmani, Mrs. ...|female|null|    0|    0|            2649|  7.225| null|       C|\n",
      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
      "only showing top 20 rows\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from langchain.llms import OpenAI\n",
    "from pyspark.sql import SparkSession\n",
    "\n",
    "spark = SparkSession.builder.getOrCreate()\n",
    "csv_file_path = \"titanic.csv\"\n",
    "df = spark.read.csv(csv_file_path, header=True, inferSchema=True)\n",
    "df.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = create_spark_dataframe_agent(llm=OpenAI(temperature=0), df=df, verbose=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to find out the size of the dataframe\n",
      "Action: python_repl_ast\n",
      "Action Input: df.count()\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'There are 891 rows in the dataframe.'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"how many rows are there?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to find out how many people have more than 3 siblings\n",
      "Action: python_repl_ast\n",
      "Action Input: df.filter(df.SibSp > 3).count()\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'30 people have more than 3 siblings.'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"how many people have more than 3 siblings\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to get the average age first\n",
      "Action: python_repl_ast\n",
      "Action Input: df.agg({\"Age\": \"mean\"}).collect()[0][0]\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now have the average age, I need to get the square root\n",
      "Action: python_repl_ast\n",
      "Action Input: math.sqrt(29.69911764705882)\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to import math first\n",
      "Action: python_repl_ast\n",
      "Action Input: import math\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now have the math library imported, I can get the square root\n",
      "Action: python_repl_ast\n",
      "Action Input: math.sqrt(29.69911764705882)\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 5.449689683556195\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'5.449689683556195'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"whats the square root of the average age?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "spark.stop()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Spark Connect Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# in apache-spark root directory. (tested here with \"spark-3.4.0-bin-hadoop3 and later\")\n",
    "# To launch Spark with support for Spark Connect sessions, run the start-connect-server.sh script.\n",
    "!./sbin/start-connect-server.sh --packages org.apache.spark:spark-connect_2.12:3.4.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "23/05/08 10:06:09 WARN Utils: Service 'SparkUI' could not bind on port 4040. Attempting port 4041.\n"
     ]
    }
   ],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "\n",
    "# Now that the Spark server is running, we can connect to it remotely using Spark Connect. We do this by \n",
    "# creating a remote Spark session on the client where our application runs. Before we can do that, we need \n",
    "# to make sure to stop the existing regular Spark session because it cannot coexist with the remote \n",
    "# Spark Connect session we are about to create.\n",
    "SparkSession.builder.master(\"local[*]\").getOrCreate().stop()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The command we used above to launch the server configured Spark to run as localhost:15002. \n",
    "# So now we can create a remote Spark session on the client using the following command.\n",
    "spark = SparkSession.builder.remote(\"sc://localhost:15002\").getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
      "|PassengerId|Survived|Pclass|                Name|   Sex| Age|SibSp|Parch|          Ticket|   Fare|Cabin|Embarked|\n",
      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
      "|          1|       0|     3|Braund, Mr. Owen ...|  male|22.0|    1|    0|       A/5 21171|   7.25| null|       S|\n",
      "|          2|       1|     1|Cumings, Mrs. Joh...|female|38.0|    1|    0|        PC 17599|71.2833|  C85|       C|\n",
      "|          3|       1|     3|Heikkinen, Miss. ...|female|26.0|    0|    0|STON/O2. 3101282|  7.925| null|       S|\n",
      "|          4|       1|     1|Futrelle, Mrs. Ja...|female|35.0|    1|    0|          113803|   53.1| C123|       S|\n",
      "|          5|       0|     3|Allen, Mr. Willia...|  male|35.0|    0|    0|          373450|   8.05| null|       S|\n",
      "|          6|       0|     3|    Moran, Mr. James|  male|null|    0|    0|          330877| 8.4583| null|       Q|\n",
      "|          7|       0|     1|McCarthy, Mr. Tim...|  male|54.0|    0|    0|           17463|51.8625|  E46|       S|\n",
      "|          8|       0|     3|Palsson, Master. ...|  male| 2.0|    3|    1|          349909| 21.075| null|       S|\n",
      "|          9|       1|     3|Johnson, Mrs. Osc...|female|27.0|    0|    2|          347742|11.1333| null|       S|\n",
      "|         10|       1|     2|Nasser, Mrs. Nich...|female|14.0|    1|    0|          237736|30.0708| null|       C|\n",
      "|         11|       1|     3|Sandstrom, Miss. ...|female| 4.0|    1|    1|         PP 9549|   16.7|   G6|       S|\n",
      "|         12|       1|     1|Bonnell, Miss. El...|female|58.0|    0|    0|          113783|  26.55| C103|       S|\n",
      "|         13|       0|     3|Saundercock, Mr. ...|  male|20.0|    0|    0|       A/5. 2151|   8.05| null|       S|\n",
      "|         14|       0|     3|Andersson, Mr. An...|  male|39.0|    1|    5|          347082| 31.275| null|       S|\n",
      "|         15|       0|     3|Vestrom, Miss. Hu...|female|14.0|    0|    0|          350406| 7.8542| null|       S|\n",
      "|         16|       1|     2|Hewlett, Mrs. (Ma...|female|55.0|    0|    0|          248706|   16.0| null|       S|\n",
      "|         17|       0|     3|Rice, Master. Eugene|  male| 2.0|    4|    1|          382652| 29.125| null|       Q|\n",
      "|         18|       1|     2|Williams, Mr. Cha...|  male|null|    0|    0|          244373|   13.0| null|       S|\n",
      "|         19|       0|     3|Vander Planke, Mr...|female|31.0|    1|    0|          345763|   18.0| null|       S|\n",
      "|         20|       1|     3|Masselmani, Mrs. ...|female|null|    0|    0|            2649|  7.225| null|       C|\n",
      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
      "only showing top 20 rows\n",
      "\n"
     ]
    }
   ],
   "source": [
    "csv_file_path = \"titanic.csv\"\n",
    "df = spark.read.csv(csv_file_path, header=True, inferSchema=True)\n",
    "df.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import create_spark_dataframe_agent\n",
    "from langchain.llms import OpenAI\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"...input your openai api key here...\"\n",
    "\n",
    "agent = create_spark_dataframe_agent(llm=OpenAI(temperature=0), df=df, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Thought: I need to find the row with the highest fare\n",
      "Action: python_repl_ast\n",
      "Action Input: df.sort(df.Fare.desc()).first()\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mRow(PassengerId=259, Survived=1, Pclass=1, Name='Ward, Miss. Anna', Sex='female', Age=35.0, SibSp=0, Parch=0, Ticket='PC 17755', Fare=512.3292, Cabin=None, Embarked='C')\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the name of the person who bought the most expensive ticket\n",
      "Final Answer: Miss. Anna Ward\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Miss. Anna Ward'"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"\"\"\n",
    "who bought the most expensive ticket?\n",
    "You can find all supported function types in https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/dataframe.html\n",
    "\"\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "spark.stop()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}