|
12 | 12 | },
|
13 | 13 | {
|
14 | 14 | "cell_type": "code",
|
15 |
| - "execution_count": 41, |
| 15 | + "execution_count": 30, |
16 | 16 | "metadata": {
|
17 | 17 | "editable": true
|
18 | 18 | },
|
|
27 | 27 | },
|
28 | 28 | {
|
29 | 29 | "cell_type": "code",
|
30 |
| - "execution_count": 42, |
| 30 | + "execution_count": 31, |
31 | 31 | "metadata": {
|
32 | 32 | "editable": true
|
33 | 33 | },
|
|
39 | 39 | },
|
40 | 40 | {
|
41 | 41 | "cell_type": "code",
|
42 |
| - "execution_count": 43, |
| 42 | + "execution_count": 32, |
43 | 43 | "metadata": {
|
44 | 44 | "editable": true
|
45 | 45 | },
|
|
72 | 72 | },
|
73 | 73 | {
|
74 | 74 | "cell_type": "code",
|
75 |
| - "execution_count": 44, |
| 75 | + "execution_count": 33, |
76 | 76 | "metadata": {
|
77 | 77 | "editable": true
|
78 | 78 | },
|
|
83 | 83 | },
|
84 | 84 | {
|
85 | 85 | "cell_type": "code",
|
86 |
| - "execution_count": 45, |
| 86 | + "execution_count": 34, |
87 | 87 | "metadata": {
|
88 | 88 | "editable": true
|
89 | 89 | },
|
|
94 | 94 | },
|
95 | 95 | {
|
96 | 96 | "cell_type": "code",
|
97 |
| - "execution_count": 46, |
| 97 | + "execution_count": 35, |
98 | 98 | "metadata": {
|
99 | 99 | "editable": true
|
100 | 100 | },
|
|
161 | 161 | "0 Keepin It Real (Skit) 0 "
|
162 | 162 | ]
|
163 | 163 | },
|
164 |
| - "execution_count": 46, |
| 164 | + "execution_count": 35, |
165 | 165 | "metadata": {},
|
166 | 166 | "output_type": "execute_result"
|
167 | 167 | }
|
|
187 | 187 | },
|
188 | 188 | {
|
189 | 189 | "cell_type": "code",
|
190 |
| - "execution_count": 47, |
| 190 | + "execution_count": 36, |
191 | 191 | "metadata": {
|
192 | 192 | "editable": true
|
193 | 193 | },
|
|
202 | 202 | " 114.78159]"
|
203 | 203 | ]
|
204 | 204 | },
|
205 |
| - "execution_count": 47, |
| 205 | + "execution_count": 36, |
206 | 206 | "metadata": {},
|
207 | 207 | "output_type": "execute_result"
|
208 | 208 | }
|
|
224 | 224 | },
|
225 | 225 | {
|
226 | 226 | "cell_type": "code",
|
227 |
| - "execution_count": 48, |
| 227 | + "execution_count": 37, |
228 | 228 | "metadata": {
|
229 | 229 | "editable": true
|
230 | 230 | },
|
|
235 | 235 | "'\\nINSERT INTO songs (song_id, title, artist_id, year, duration)\\nVALUES (%s, %s, %s, %s, %s) ON CONFLICT DO NOTHING;\\n'"
|
236 | 236 | ]
|
237 | 237 | },
|
238 |
| - "execution_count": 48, |
| 238 | + "execution_count": 37, |
239 | 239 | "metadata": {},
|
240 | 240 | "output_type": "execute_result"
|
241 | 241 | }
|
|
246 | 246 | },
|
247 | 247 | {
|
248 | 248 | "cell_type": "code",
|
249 |
| - "execution_count": 49, |
| 249 | + "execution_count": 38, |
250 | 250 | "metadata": {
|
251 | 251 | "editable": true
|
252 | 252 | },
|
|
281 | 281 | },
|
282 | 282 | {
|
283 | 283 | "cell_type": "code",
|
284 |
| - "execution_count": 50, |
| 284 | + "execution_count": 39, |
285 | 285 | "metadata": {
|
286 | 286 | "editable": true
|
287 | 287 | },
|
|
292 | 292 | "['ARD0S291187B9B7BF5', 'Rated R', 'Ohio', nan, nan]"
|
293 | 293 | ]
|
294 | 294 | },
|
295 |
| - "execution_count": 50, |
| 295 | + "execution_count": 39, |
296 | 296 | "metadata": {},
|
297 | 297 | "output_type": "execute_result"
|
298 | 298 | }
|
|
314 | 314 | },
|
315 | 315 | {
|
316 | 316 | "cell_type": "code",
|
317 |
| - "execution_count": 51, |
| 317 | + "execution_count": 40, |
318 | 318 | "metadata": {
|
319 | 319 | "editable": true
|
320 | 320 | },
|
|
350 | 350 | },
|
351 | 351 | {
|
352 | 352 | "cell_type": "code",
|
353 |
| - "execution_count": 52, |
| 353 | + "execution_count": 41, |
354 | 354 | "metadata": {
|
355 | 355 | "editable": true
|
356 | 356 | },
|
|
361 | 361 | },
|
362 | 362 | {
|
363 | 363 | "cell_type": "code",
|
364 |
| - "execution_count": 53, |
| 364 | + "execution_count": 42, |
365 | 365 | "metadata": {
|
366 | 366 | "editable": true
|
367 | 367 | },
|
|
372 | 372 | },
|
373 | 373 | {
|
374 | 374 | "cell_type": "code",
|
375 |
| - "execution_count": 54, |
| 375 | + "execution_count": 43, |
376 | 376 | "metadata": {
|
377 | 377 | "editable": true
|
378 | 378 | },
|
|
565 | 565 | "4 24 "
|
566 | 566 | ]
|
567 | 567 | },
|
568 |
| - "execution_count": 54, |
| 568 | + "execution_count": 43, |
569 | 569 | "metadata": {},
|
570 | 570 | "output_type": "execute_result"
|
571 | 571 | }
|
|
595 | 595 | },
|
596 | 596 | {
|
597 | 597 | "cell_type": "code",
|
598 |
| - "execution_count": 55, |
| 598 | + "execution_count": 44, |
599 | 599 | "metadata": {
|
600 | 600 | "editable": true
|
601 | 601 | },
|
|
788 | 788 | "4 24 "
|
789 | 789 | ]
|
790 | 790 | },
|
791 |
| - "execution_count": 55, |
| 791 | + "execution_count": 44, |
792 | 792 | "metadata": {},
|
793 | 793 | "output_type": "execute_result"
|
794 | 794 | }
|
|
800 | 800 | },
|
801 | 801 | {
|
802 | 802 | "cell_type": "code",
|
803 |
| - "execution_count": 56, |
| 803 | + "execution_count": 45, |
804 | 804 | "metadata": {
|
805 | 805 | "editable": true
|
806 | 806 | },
|
|
816 | 816 | "Name: ts, dtype: datetime64[ns]"
|
817 | 817 | ]
|
818 | 818 | },
|
819 |
| - "execution_count": 56, |
| 819 | + "execution_count": 45, |
820 | 820 | "metadata": {},
|
821 | 821 | "output_type": "execute_result"
|
822 | 822 | }
|
|
830 | 830 | },
|
831 | 831 | {
|
832 | 832 | "cell_type": "code",
|
833 |
| - "execution_count": 57, |
| 833 | + "execution_count": 46, |
834 | 834 | "metadata": {
|
835 | 835 | "editable": true
|
836 | 836 | },
|
|
842 | 842 | },
|
843 | 843 | {
|
844 | 844 | "cell_type": "code",
|
845 |
| - "execution_count": 58, |
| 845 | + "execution_count": 47, |
846 | 846 | "metadata": {
|
847 | 847 | "editable": true
|
848 | 848 | },
|
|
941 | 941 | "4 2018-11-29 00:07:13.796 0 29 48 11 2018 3"
|
942 | 942 | ]
|
943 | 943 | },
|
944 |
| - "execution_count": 58, |
| 944 | + "execution_count": 47, |
945 | 945 | "metadata": {},
|
946 | 946 | "output_type": "execute_result"
|
947 | 947 | }
|
|
963 | 963 | },
|
964 | 964 | {
|
965 | 965 | "cell_type": "code",
|
966 |
| - "execution_count": 59, |
| 966 | + "execution_count": 48, |
967 | 967 | "metadata": {
|
968 | 968 | "editable": true
|
969 | 969 | },
|
|
996 | 996 | },
|
997 | 997 | {
|
998 | 998 | "cell_type": "code",
|
999 |
| - "execution_count": 60, |
| 999 | + "execution_count": 55, |
1000 | 1000 | "metadata": {
|
1001 | 1001 | "editable": true
|
1002 | 1002 | },
|
1003 | 1003 | "outputs": [],
|
1004 | 1004 | "source": [
|
1005 |
| - "user_df = df[[\"userId\", \"firstName\", \"lastName\", \"gender\", \"level\"]]\n" |
| 1005 | + "user_df = df[[\"userId\", \"firstName\", \"lastName\", \"gender\", \"level\"]]\n", |
| 1006 | + "user_df.head()\n", |
| 1007 | + "user_df = user_df.rename(columns={\"userId\": \"user_id\", \"firstName\": \"first_name\", \"lastName\":\"last_name\"})\n", |
| 1008 | + "user_df = user_df.drop_duplicates(subset=['user_id'])" |
1006 | 1009 | ]
|
1007 | 1010 | },
|
1008 | 1011 | {
|
|
1017 | 1020 | },
|
1018 | 1021 | {
|
1019 | 1022 | "cell_type": "code",
|
1020 |
| - "execution_count": 61, |
| 1023 | + "execution_count": 50, |
| 1024 | + "metadata": { |
| 1025 | + "editable": true |
| 1026 | + }, |
| 1027 | + "outputs": [], |
| 1028 | + "source": [ |
| 1029 | + "from sqlalchemy import create_engine\n", |
| 1030 | + "# conn = psycopg2.connect(\"host=127.0.0.1 dbname=sparkifydb user=student password=student\")\n", |
| 1031 | + "engine = create_engine('postgresql+psycopg2://student:student@localhost/sparkifydb')" |
| 1032 | + ] |
| 1033 | + }, |
| 1034 | + { |
| 1035 | + "cell_type": "code", |
| 1036 | + "execution_count": 56, |
| 1037 | + "metadata": { |
| 1038 | + "editable": true |
| 1039 | + }, |
| 1040 | + "outputs": [], |
| 1041 | + "source": [ |
| 1042 | + "delete_user_table = (\"\"\"\n", |
| 1043 | + "DELETE FROM users\n", |
| 1044 | + ";\n", |
| 1045 | + "\"\"\")\n", |
| 1046 | + "cur.execute(delete_user_table)" |
| 1047 | + ] |
| 1048 | + }, |
| 1049 | + { |
| 1050 | + "cell_type": "code", |
| 1051 | + "execution_count": 57, |
| 1052 | + "metadata": { |
| 1053 | + "editable": true |
| 1054 | + }, |
| 1055 | + "outputs": [], |
| 1056 | + "source": [ |
| 1057 | + "user_df.to_sql('users', con = engine, if_exists = 'append', chunksize = 1000, index = False)" |
| 1058 | + ] |
| 1059 | + }, |
| 1060 | + { |
| 1061 | + "cell_type": "code", |
| 1062 | + "execution_count": 27, |
| 1063 | + "metadata": { |
| 1064 | + "editable": true |
| 1065 | + }, |
| 1066 | + "outputs": [], |
| 1067 | + "source": [ |
| 1068 | + "# rows = []\n", |
| 1069 | + "# for row in user_df.iterrows():\n", |
| 1070 | + "# rows.append(row)" |
| 1071 | + ] |
| 1072 | + }, |
| 1073 | + { |
| 1074 | + "cell_type": "code", |
| 1075 | + "execution_count": 29, |
1021 | 1076 | "metadata": {
|
1022 | 1077 | "editable": true
|
1023 | 1078 | },
|
|
1099 | 1154 | },
|
1100 | 1155 | {
|
1101 | 1156 | "cell_type": "code",
|
1102 |
| - "execution_count": 63, |
| 1157 | + "execution_count": 59, |
1103 | 1158 | "metadata": {
|
1104 | 1159 | "editable": true
|
1105 | 1160 | },
|
|
0 commit comments