├── 1800.csv
├── LICENSE
├── Marvel-graph.txt
├── Marvel-names.txt
├── README.md
├── book.txt
├── customer-orders.csv
├── degrees-of-separation.py
├── fakefriends.csv
├── friends-by-age.py
├── max-temperatures.py
├── min-temperatures.py
├── most-popular-superhero.py
├── movie-recommendations-als-1m.py
├── movie-recommendations-als.py
├── movie-similarities-1m.py
├── movie-similarities-cluster.py
├── movie-similarities.py
├── popular-movies-dataframe.py
├── popular-movies-nicer.py
├── popular-movies.py
├── ratings-counter.py
├── regression.txt
├── spark-linear-regression.py
├── spark-sql.py
├── total-spent-by-customer-sorted.py
├── total-spent-by-customer.py
├── word-count-better-sorted.py
├── word-count-better.py
└── word-count.py


/1800.csv:
--------------------------------------------------------------------------------
   1 | ITE00100554,18000101,TMAX,-75,,,E,
   2 | ITE00100554,18000101,TMIN,-148,,,E,
   3 | GM000010962,18000101,PRCP,0,,,E,
   4 | EZE00100082,18000101,TMAX,-86,,,E,
   5 | EZE00100082,18000101,TMIN,-135,,,E,
   6 | ITE00100554,18000102,TMAX,-60,,I,E,
   7 | ITE00100554,18000102,TMIN,-125,,,E,
   8 | GM000010962,18000102,PRCP,0,,,E,
   9 | EZE00100082,18000102,TMAX,-44,,,E,
  10 | EZE00100082,18000102,TMIN,-130,,,E,
  11 | ITE00100554,18000103,TMAX,-23,,,E,
  12 | ITE00100554,18000103,TMIN,-46,,I,E,
  13 | GM000010962,18000103,PRCP,4,,,E,
  14 | EZE00100082,18000103,TMAX,-10,,,E,
  15 | EZE00100082,18000103,TMIN,-73,,,E,
  16 | ITE00100554,18000104,TMAX,0,,,E,
  17 | ITE00100554,18000104,TMIN,-13,,,E,
  18 | GM000010962,18000104,PRCP,0,,,E,
  19 | EZE00100082,18000104,TMAX,-55,,,E,
  20 | EZE00100082,18000104,TMIN,-74,,,E,
  21 | ITE00100554,18000105,TMAX,10,,,E,
  22 | ITE00100554,18000105,TMIN,-6,,,E,
  23 | GM000010962,18000105,PRCP,0,,,E,
  24 | EZE00100082,18000105,TMAX,-40,,,E,
  25 | EZE00100082,18000105,TMIN,-58,,,E,
  26 | ITE00100554,18000106,TMAX,13,,,E,
  27 | ITE00100554,18000106,TMIN,13,,,E,
  28 | GM000010962,18000106,PRCP,0,,,E,
  29 | EZE00100082,18000106,TMAX,-39,,,E,
  30 | EZE00100082,18000106,TMIN,-57,,,E,
  31 | ITE00100554,18000107,TMAX,31,,,E,
  32 | ITE00100554,18000107,TMIN,10,,,E,
  33 | GM000010962,18000107,PRCP,0,,,E,
  34 | EZE00100082,18000107,TMAX,-30,,,E,
  35 | EZE00100082,18000107,TMIN,-50,,,E,
  36 | ITE00100554,18000108,TMAX,29,,,E,
  37 | ITE00100554,18000108,TMIN,14,,,E,
  38 | GM000010962,18000108,PRCP,0,,,E,
  39 | EZE00100082,18000108,TMAX,-1,,,E,
  40 | EZE00100082,18000108,TMIN,-31,,,E,
  41 | ITE00100554,18000109,TMAX,35,,,E,
  42 | ITE00100554,18000109,TMIN,23,,,E,
  43 | GM000010962,18000109,PRCP,0,,,E,
  44 | EZE00100082,18000109,TMAX,5,,,E,
  45 | EZE00100082,18000109,TMIN,-46,,,E,
  46 | ITE00100554,18000110,TMAX,46,,,E,
  47 | ITE00100554,18000110,TMIN,31,,,E,
  48 | GM000010962,18000110,PRCP,0,,,E,
  49 | EZE00100082,18000110,TMAX,-46,,,E,
  50 | EZE00100082,18000110,TMIN,-75,,,E,
  51 | ITE00100554,18000111,TMAX,66,,,E,
  52 | ITE00100554,18000111,TMIN,41,,,E,
  53 | GM000010962,18000111,PRCP,31,,,E,
  54 | EZE00100082,18000111,TMAX,1,,,E,
  55 | EZE00100082,18000111,TMIN,-62,,,E,
  56 | ITE00100554,18000112,TMAX,41,,,E,
  57 | ITE00100554,18000112,TMIN,29,,,E,
  58 | GM000010962,18000112,PRCP,0,,,E,
  59 | EZE00100082,18000112,TMAX,-33,,,E,
  60 | EZE00100082,18000112,TMIN,-60,,,E,
  61 | ITE00100554,18000113,TMAX,23,,,E,
  62 | ITE00100554,18000113,TMIN,13,,,E,
  63 | GM000010962,18000113,PRCP,3,,,E,
  64 | EZE00100082,18000113,TMAX,-20,,,E,
  65 | EZE00100082,18000113,TMIN,-60,,,E,
  66 | ITE00100554,18000114,TMAX,41,,,E,
  67 | ITE00100554,18000114,TMIN,23,,,E,
  68 | GM000010962,18000114,PRCP,0,,,E,
  69 | EZE00100082,18000114,TMAX,0,,,E,
  70 | EZE00100082,18000114,TMIN,-35,,,E,
  71 | ITE00100554,18000115,TMAX,54,,,E,
  72 | ITE00100554,18000115,TMIN,41,,,E,
  73 | GM000010962,18000115,PRCP,0,,,E,
  74 | EZE00100082,18000115,TMAX,10,,,E,
  75 | EZE00100082,18000115,TMIN,-23,,,E,
  76 | ITE00100554,18000116,TMAX,56,,,E,
  77 | ITE00100554,18000116,TMIN,41,,,E,
  78 | GM000010962,18000116,PRCP,0,,,E,
  79 | EZE00100082,18000116,TMAX,-11,,,E,
  80 | EZE00100082,18000116,TMIN,-37,,,E,
  81 | ITE00100554,18000117,TMAX,84,,,E,
  82 | ITE00100554,18000117,TMIN,48,,,E,
  83 | GM000010962,18000117,PRCP,0,,,E,
  84 | EZE00100082,18000117,TMAX,14,,,E,
  85 | EZE00100082,18000117,TMIN,-35,,,E,
  86 | ITE00100554,18000118,TMAX,59,,,E,
  87 | ITE00100554,18000118,TMIN,46,,,E,
  88 | GM000010962,18000118,PRCP,2,,,E,
  89 | EZE00100082,18000118,TMAX,47,,,E,
  90 | EZE00100082,18000118,TMIN,9,,,E,
  91 | ITE00100554,18000119,TMAX,59,,,E,
  92 | ITE00100554,18000119,TMIN,50,,,E,
  93 | GM000010962,18000119,PRCP,0,,,E,
  94 | EZE00100082,18000119,TMAX,66,,,E,
  95 | EZE00100082,18000119,TMIN,34,,,E,
  96 | ITE00100554,18000120,TMAX,60,,,E,
  97 | ITE00100554,18000120,TMIN,25,,,E,
  98 | GM000010962,18000120,PRCP,4,,,E,
  99 | EZE00100082,18000120,TMAX,58,,,E,
 100 | EZE00100082,18000120,TMIN,17,,,E,
 101 | ITE00100554,18000121,TMAX,80,,,E,
 102 | ITE00100554,18000121,TMIN,30,,,E,
 103 | GM000010962,18000121,PRCP,6,,,E,
 104 | EZE00100082,18000121,TMAX,31,,,E,
 105 | EZE00100082,18000121,TMIN,8,,,E,
 106 | ITE00100554,18000122,TMAX,81,,,E,
 107 | ITE00100554,18000122,TMIN,74,,,E,
 108 | GM000010962,18000122,PRCP,68,,,E,
 109 | EZE00100082,18000122,TMAX,8,,,E,
 110 | EZE00100082,18000122,TMIN,-16,,,E,
 111 | ITE00100554,18000123,TMAX,85,,,E,
 112 | ITE00100554,18000123,TMIN,75,,,E,
 113 | GM000010962,18000123,PRCP,18,,,E,
 114 | EZE00100082,18000123,TMAX,18,,,E,
 115 | EZE00100082,18000123,TMIN,-16,,,E,
 116 | ITE00100554,18000124,TMAX,85,,,E,
 117 | ITE00100554,18000124,TMIN,75,,,E,
 118 | GM000010962,18000124,PRCP,0,,,E,
 119 | EZE00100082,18000124,TMAX,31,,,E,
 120 | EZE00100082,18000124,TMIN,-3,,,E,
 121 | ITE00100554,18000125,TMAX,98,,,E,
 122 | ITE00100554,18000125,TMIN,75,,,E,
 123 | GM000010962,18000125,PRCP,0,,,E,
 124 | EZE00100082,18000125,TMAX,35,,,E,
 125 | EZE00100082,18000125,TMIN,2,,,E,
 126 | ITE00100554,18000126,TMAX,75,,,E,
 127 | ITE00100554,18000126,TMIN,34,,,E,
 128 | GM000010962,18000126,PRCP,0,,,E,
 129 | EZE00100082,18000126,TMAX,44,,,E,
 130 | EZE00100082,18000126,TMIN,16,,,E,
 131 | ITE00100554,18000127,TMAX,73,,,E,
 132 | ITE00100554,18000127,TMIN,29,,,E,
 133 | GM000010962,18000127,PRCP,0,,,E,
 134 | EZE00100082,18000127,TMAX,57,,,E,
 135 | EZE00100082,18000127,TMIN,15,,,E,
 136 | ITE00100554,18000128,TMAX,79,,,E,
 137 | ITE00100554,18000128,TMIN,54,,,E,
 138 | GM000010962,18000128,PRCP,4,,,E,
 139 | EZE00100082,18000128,TMAX,69,,,E,
 140 | EZE00100082,18000128,TMIN,33,,,E,
 141 | ITE00100554,18000129,TMAX,73,,,E,
 142 | ITE00100554,18000129,TMIN,50,,,E,
 143 | GM000010962,18000129,PRCP,0,,,E,
 144 | EZE00100082,18000129,TMAX,67,,,E,
 145 | EZE00100082,18000129,TMIN,19,,,E,
 146 | ITE00100554,18000130,TMAX,66,,,E,
 147 | ITE00100554,18000130,TMIN,50,,,E,
 148 | GM000010962,18000130,PRCP,0,,,E,
 149 | EZE00100082,18000130,TMAX,29,,,E,
 150 | EZE00100082,18000130,TMIN,3,,,E,
 151 | ITE00100554,18000131,TMAX,85,,,E,
 152 | ITE00100554,18000131,TMIN,50,,,E,
 153 | GM000010962,18000131,PRCP,0,,,E,
 154 | EZE00100082,18000131,TMAX,62,,,E,
 155 | EZE00100082,18000131,TMIN,23,,,E,
 156 | ITE00100554,18000201,TMAX,91,,,E,
 157 | ITE00100554,18000201,TMIN,63,,,E,
 158 | GM000010962,18000201,PRCP,13,,,E,
 159 | EZE00100082,18000201,TMAX,48,,,E,
 160 | EZE00100082,18000201,TMIN,17,,,E,
 161 | ITE00100554,18000202,TMAX,66,,,E,
 162 | ITE00100554,18000202,TMIN,54,,,E,
 163 | GM000010962,18000202,PRCP,16,,,E,
 164 | EZE00100082,18000202,TMAX,67,,,E,
 165 | EZE00100082,18000202,TMIN,19,,,E,
 166 | ITE00100554,18000203,TMAX,56,,,E,
 167 | ITE00100554,18000203,TMIN,54,,,E,
 168 | GM000010962,18000203,PRCP,0,,,E,
 169 | EZE00100082,18000203,TMAX,53,,,E,
 170 | EZE00100082,18000203,TMIN,2,,,E,
 171 | ITE00100554,18000204,TMAX,104,,,E,
 172 | ITE00100554,18000204,TMIN,59,,,E,
 173 | GM000010962,18000204,PRCP,0,,,E,
 174 | EZE00100082,18000204,TMAX,66,,,E,
 175 | EZE00100082,18000204,TMIN,39,,,E,
 176 | ITE00100554,18000205,TMAX,79,,,E,
 177 | ITE00100554,18000205,TMIN,46,,,E,
 178 | GM000010962,18000205,PRCP,0,,,E,
 179 | EZE00100082,18000205,TMAX,59,,,E,
 180 | EZE00100082,18000205,TMIN,22,,,E,
 181 | ITE00100554,18000206,TMAX,75,,,E,
 182 | ITE00100554,18000206,TMIN,41,,,E,
 183 | GM000010962,18000206,PRCP,0,,,E,
 184 | EZE00100082,18000206,TMAX,24,,,E,
 185 | EZE00100082,18000206,TMIN,-3,,,E,
 186 | ITE00100554,18000207,TMAX,73,,,E,
 187 | ITE00100554,18000207,TMIN,35,,,E,
 188 | GM000010962,18000207,PRCP,6,,,E,
 189 | EZE00100082,18000207,TMAX,4,,,E,
 190 | EZE00100082,18000207,TMIN,-22,,,E,
 191 | ITE00100554,18000208,TMAX,50,,,E,
 192 | ITE00100554,18000208,TMIN,25,,,E,
 193 | GM000010962,18000208,PRCP,0,,,E,
 194 | EZE00100082,18000208,TMAX,-20,,,E,
 195 | EZE00100082,18000208,TMIN,-39,,,E,
 196 | ITE00100554,18000209,TMAX,35,,,E,
 197 | ITE00100554,18000209,TMIN,0,,,E,
 198 | GM000010962,18000209,PRCP,0,,,E,
 199 | EZE00100082,18000209,TMAX,-17,,,E,
 200 | EZE00100082,18000209,TMIN,-36,,,E,
 201 | ITE00100554,18000210,TMAX,38,,,E,
 202 | ITE00100554,18000210,TMIN,16,,,E,
 203 | GM000010962,18000210,PRCP,0,,,E,
 204 | EZE00100082,18000210,TMAX,-25,,,E,
 205 | EZE00100082,18000210,TMIN,-69,,,E,
 206 | ITE00100554,18000211,TMAX,21,,,E,
 207 | ITE00100554,18000211,TMIN,9,,,E,
 208 | GM000010962,18000211,PRCP,0,,,E,
 209 | EZE00100082,18000211,TMAX,-34,,,E,
 210 | EZE00100082,18000211,TMIN,-102,,,E,
 211 | ITE00100554,18000212,TMAX,13,,,E,
 212 | ITE00100554,18000212,TMIN,3,,,E,
 213 | GM000010962,18000212,PRCP,0,,,E,
 214 | EZE00100082,18000212,TMAX,-22,,,E,
 215 | EZE00100082,18000212,TMIN,-78,,,E,
 216 | ITE00100554,18000213,TMAX,13,,,E,
 217 | ITE00100554,18000213,TMIN,0,,,E,
 218 | GM000010962,18000213,PRCP,0,,,E,
 219 | EZE00100082,18000213,TMAX,1,,,E,
 220 | EZE00100082,18000213,TMIN,-42,,,E,
 221 | ITE00100554,18000214,TMAX,13,,,E,
 222 | ITE00100554,18000214,TMIN,0,,,E,
 223 | GM000010962,18000214,PRCP,0,,,E,
 224 | EZE00100082,18000214,TMAX,5,,,E,
 225 | EZE00100082,18000214,TMIN,-35,,,E,
 226 | ITE00100554,18000215,TMAX,21,,,E,
 227 | ITE00100554,18000215,TMIN,13,,,E,
 228 | GM000010962,18000215,PRCP,0,,,E,
 229 | EZE00100082,18000215,TMAX,18,,,E,
 230 | EZE00100082,18000215,TMIN,0,,,E,
 231 | ITE00100554,18000216,TMAX,75,,,E,
 232 | ITE00100554,18000216,TMIN,13,,,E,
 233 | GM000010962,18000216,PRCP,7,,,E,
 234 | EZE00100082,18000216,TMAX,24,,,E,
 235 | EZE00100082,18000216,TMIN,-6,,,E,
 236 | ITE00100554,18000217,TMAX,71,,,E,
 237 | ITE00100554,18000217,TMIN,23,,,E,
 238 | GM000010962,18000217,PRCP,0,,,E,
 239 | EZE00100082,18000217,TMAX,20,,,E,
 240 | EZE00100082,18000217,TMIN,-13,,,E,
 241 | ITE00100554,18000218,TMAX,48,,,E,
 242 | ITE00100554,18000218,TMIN,21,,,E,
 243 | GM000010962,18000218,PRCP,0,,,E,
 244 | EZE00100082,18000218,TMAX,0,,,E,
 245 | EZE00100082,18000218,TMIN,-52,,,E,
 246 | ITE00100554,18000219,TMAX,50,,,E,
 247 | ITE00100554,18000219,TMIN,38,,,E,
 248 | GM000010962,18000219,PRCP,0,,,E,
 249 | EZE00100082,18000219,TMAX,-6,,,E,
 250 | EZE00100082,18000219,TMIN,-50,,,E,
 251 | ITE00100554,18000220,TMAX,66,,,E,
 252 | ITE00100554,18000220,TMIN,38,,,E,
 253 | GM000010962,18000220,PRCP,0,,,E,
 254 | EZE00100082,18000220,TMAX,-34,,,E,
 255 | EZE00100082,18000220,TMIN,-72,,,E,
 256 | ITE00100554,18000221,TMAX,66,,,E,
 257 | ITE00100554,18000221,TMIN,25,,,E,
 258 | GM000010962,18000221,PRCP,0,,,E,
 259 | EZE00100082,18000221,TMAX,-16,,,E,
 260 | EZE00100082,18000221,TMIN,-60,,,E,
 261 | ITE00100554,18000222,TMAX,63,,,E,
 262 | ITE00100554,18000222,TMIN,48,,,E,
 263 | GM000010962,18000222,PRCP,0,,,E,
 264 | EZE00100082,18000222,TMAX,33,,,E,
 265 | EZE00100082,18000222,TMIN,-42,,,E,
 266 | ITE00100554,18000223,TMAX,81,,,E,
 267 | ITE00100554,18000223,TMIN,54,,,E,
 268 | GM000010962,18000223,PRCP,0,,,E,
 269 | EZE00100082,18000223,TMAX,40,,,E,
 270 | EZE00100082,18000223,TMIN,17,,,E,
 271 | ITE00100554,18000224,TMAX,104,,,E,
 272 | ITE00100554,18000224,TMIN,73,,,E,
 273 | GM000010962,18000224,PRCP,0,,,E,
 274 | EZE00100082,18000224,TMAX,56,,,E,
 275 | EZE00100082,18000224,TMIN,14,,,E,
 276 | ITE00100554,18000225,TMAX,116,,,E,
 277 | ITE00100554,18000225,TMIN,60,,,E,
 278 | GM000010962,18000225,PRCP,0,,,E,
 279 | EZE00100082,18000225,TMAX,20,,,E,
 280 | EZE00100082,18000225,TMIN,4,,,E,
 281 | ITE00100554,18000226,TMAX,129,,,E,
 282 | ITE00100554,18000226,TMIN,88,,,E,
 283 | GM000010962,18000226,PRCP,0,,,E,
 284 | EZE00100082,18000226,TMAX,15,,,E,
 285 | EZE00100082,18000226,TMIN,-57,,,E,
 286 | ITE00100554,18000227,TMAX,100,,,E,
 287 | ITE00100554,18000227,TMIN,88,,I,E,
 288 | GM000010962,18000227,PRCP,6,,,E,
 289 | EZE00100082,18000227,TMAX,-39,,,E,
 290 | EZE00100082,18000227,TMIN,-74,,,E,
 291 | ITE00100554,18000228,TMAX,75,,I,E,
 292 | ITE00100554,18000228,TMIN,63,,,E,
 293 | GM000010962,18000228,PRCP,0,,,E,
 294 | EZE00100082,18000228,TMAX,25,,,E,
 295 | EZE00100082,18000228,TMIN,-43,,,E,
 296 | ITE00100554,18000301,TMAX,100,,,E,
 297 | ITE00100554,18000301,TMIN,66,,,E,
 298 | GM000010962,18000301,PRCP,42,,,E,
 299 | EZE00100082,18000301,TMAX,-21,,,E,
 300 | EZE00100082,18000301,TMIN,-37,,,E,
 301 | ITE00100554,18000302,TMAX,79,,,E,
 302 | ITE00100554,18000302,TMIN,60,,,E,
 303 | GM000010962,18000302,PRCP,16,,,E,
 304 | EZE00100082,18000302,TMAX,4,,,E,
 305 | EZE00100082,18000302,TMIN,-40,,,E,
 306 | ITE00100554,18000303,TMAX,54,,,E,
 307 | ITE00100554,18000303,TMIN,46,,,E,
 308 | GM000010962,18000303,PRCP,6,,,E,
 309 | EZE00100082,18000303,TMAX,10,,,E,
 310 | EZE00100082,18000303,TMIN,-30,,,E,
 311 | ITE00100554,18000304,TMAX,84,,,E,
 312 | ITE00100554,18000304,TMIN,29,,,E,
 313 | GM000010962,18000304,PRCP,0,,,E,
 314 | EZE00100082,18000304,TMAX,32,,,E,
 315 | EZE00100082,18000304,TMIN,-23,,,E,
 316 | ITE00100554,18000305,TMAX,79,,,E,
 317 | ITE00100554,18000305,TMIN,21,,,E,
 318 | GM000010962,18000305,PRCP,4,,,E,
 319 | EZE00100082,18000305,TMAX,-14,,,E,
 320 | EZE00100082,18000305,TMIN,-47,,,E,
 321 | ITE00100554,18000306,TMAX,60,,,E,
 322 | ITE00100554,18000306,TMIN,29,,,E,
 323 | GM000010962,18000306,PRCP,0,,,E,
 324 | EZE00100082,18000306,TMAX,-34,,,E,
 325 | EZE00100082,18000306,TMIN,-70,,,E,
 326 | ITE00100554,18000307,TMAX,34,,,E,
 327 | ITE00100554,18000307,TMIN,16,,,E,
 328 | GM000010962,18000307,PRCP,0,,,E,
 329 | EZE00100082,18000307,TMAX,-42,,,E,
 330 | EZE00100082,18000307,TMIN,-89,,,E,
 331 | ITE00100554,18000308,TMAX,38,,,E,
 332 | ITE00100554,18000308,TMIN,0,,,E,
 333 | GM000010962,18000308,PRCP,0,,,E,
 334 | EZE00100082,18000308,TMAX,-49,,,E,
 335 | EZE00100082,18000308,TMIN,-130,,,E,
 336 | ITE00100554,18000309,TMAX,79,,,E,
 337 | ITE00100554,18000309,TMIN,16,,,E,
 338 | GM000010962,18000309,PRCP,30,,,E,
 339 | EZE00100082,18000309,TMAX,-63,,,E,
 340 | EZE00100082,18000309,TMIN,-93,,,E,
 341 | ITE00100554,18000310,TMAX,75,,,E,
 342 | ITE00100554,18000310,TMIN,25,,,E,
 343 | GM000010962,18000310,PRCP,0,,,E,
 344 | EZE00100082,18000310,TMAX,-34,,,E,
 345 | EZE00100082,18000310,TMIN,-110,,,E,
 346 | ITE00100554,18000311,TMAX,79,,,E,
 347 | ITE00100554,18000311,TMIN,29,,,E,
 348 | GM000010962,18000311,PRCP,0,,,E,
 349 | EZE00100082,18000311,TMAX,-33,,,E,
 350 | EZE00100082,18000311,TMIN,-107,,,E,
 351 | ITE00100554,18000312,TMAX,69,,,E,
 352 | ITE00100554,18000312,TMIN,41,,,E,
 353 | GM000010962,18000312,PRCP,7,,,E,
 354 | EZE00100082,18000312,TMAX,-22,,,E,
 355 | EZE00100082,18000312,TMIN,-87,,,E,
 356 | ITE00100554,18000313,TMAX,75,,,E,
 357 | ITE00100554,18000313,TMIN,44,,,E,
 358 | GM000010962,18000313,PRCP,0,,,E,
 359 | EZE00100082,18000313,TMAX,-24,,,E,
 360 | EZE00100082,18000313,TMIN,-110,,,E,
 361 | ITE00100554,18000314,TMAX,100,,,E,
 362 | ITE00100554,18000314,TMIN,25,,,E,
 363 | GM000010962,18000314,PRCP,0,,,E,
 364 | EZE00100082,18000314,TMAX,11,,,E,
 365 | EZE00100082,18000314,TMIN,-61,,,E,
 366 | ITE00100554,18000315,TMAX,109,,,E,
 367 | ITE00100554,18000315,TMIN,50,,,E,
 368 | GM000010962,18000315,PRCP,0,,,E,
 369 | EZE00100082,18000315,TMAX,-1,,,E,
 370 | EZE00100082,18000315,TMIN,-52,,,E,
 371 | ITE00100554,18000316,TMAX,113,,,E,
 372 | ITE00100554,18000316,TMIN,35,,,E,
 373 | GM000010962,18000316,PRCP,0,,,E,
 374 | EZE00100082,18000316,TMAX,10,,,E,
 375 | EZE00100082,18000316,TMIN,-67,,,E,
 376 | ITE00100554,18000317,TMAX,109,,,E,
 377 | ITE00100554,18000317,TMIN,54,,,E,
 378 | GM000010962,18000317,PRCP,0,,,E,
 379 | EZE00100082,18000317,TMAX,30,,,E,
 380 | EZE00100082,18000317,TMIN,-52,,,E,
 381 | ITE00100554,18000318,TMAX,91,,,E,
 382 | ITE00100554,18000318,TMIN,56,,,E,
 383 | GM000010962,18000318,PRCP,4,,,E,
 384 | EZE00100082,18000318,TMAX,26,,,E,
 385 | EZE00100082,18000318,TMIN,-35,,,E,
 386 | ITE00100554,18000319,TMAX,125,,,E,
 387 | ITE00100554,18000319,TMIN,60,,,E,
 388 | GM000010962,18000319,PRCP,17,,,E,
 389 | EZE00100082,18000319,TMAX,36,,,E,
 390 | EZE00100082,18000319,TMIN,-19,,,E,
 391 | ITE00100554,18000320,TMAX,116,,,E,
 392 | ITE00100554,18000320,TMIN,73,,,E,
 393 | GM000010962,18000320,PRCP,20,,,E,
 394 | EZE00100082,18000320,TMAX,13,,,E,
 395 | EZE00100082,18000320,TMIN,-38,,,E,
 396 | ITE00100554,18000321,TMAX,109,,,E,
 397 | ITE00100554,18000321,TMIN,50,,,E,
 398 | GM000010962,18000321,PRCP,6,,,E,
 399 | EZE00100082,18000321,TMAX,15,,,E,
 400 | EZE00100082,18000321,TMIN,-48,,,E,
 401 | ITE00100554,18000322,TMAX,71,,,E,
 402 | ITE00100554,18000322,TMIN,48,,,E,
 403 | GM000010962,18000322,PRCP,25,,,E,
 404 | EZE00100082,18000322,TMAX,14,,,E,
 405 | EZE00100082,18000322,TMIN,-57,,,E,
 406 | ITE00100554,18000323,TMAX,75,,,E,
 407 | ITE00100554,18000323,TMIN,19,,,E,
 408 | GM000010962,18000323,PRCP,4,,,E,
 409 | EZE00100082,18000323,TMAX,4,,,E,
 410 | EZE00100082,18000323,TMIN,-78,,,E,
 411 | ITE00100554,18000324,TMAX,81,,,E,
 412 | ITE00100554,18000324,TMIN,10,,,E,
 413 | GM000010962,18000324,PRCP,0,,,E,
 414 | EZE00100082,18000324,TMAX,33,,,E,
 415 | EZE00100082,18000324,TMIN,-24,,,E,
 416 | ITE00100554,18000325,TMAX,85,,,E,
 417 | ITE00100554,18000325,TMIN,25,,,E,
 418 | GM000010962,18000325,PRCP,0,,,E,
 419 | EZE00100082,18000325,TMAX,68,,,E,
 420 | EZE00100082,18000325,TMIN,8,,,E,
 421 | ITE00100554,18000326,TMAX,110,,,E,
 422 | ITE00100554,18000326,TMIN,31,,,E,
 423 | GM000010962,18000326,PRCP,0,,,E,
 424 | EZE00100082,18000326,TMAX,71,,,E,
 425 | EZE00100082,18000326,TMIN,9,,,E,
 426 | ITE00100554,18000327,TMAX,113,,,E,
 427 | ITE00100554,18000327,TMIN,48,,,E,
 428 | GM000010962,18000327,PRCP,0,,,E,
 429 | EZE00100082,18000327,TMAX,84,,,E,
 430 | EZE00100082,18000327,TMIN,-5,,,E,
 431 | ITE00100554,18000328,TMAX,125,,,E,
 432 | ITE00100554,18000328,TMIN,54,,,E,
 433 | GM000010962,18000328,PRCP,0,,,E,
 434 | EZE00100082,18000328,TMAX,86,,,E,
 435 | EZE00100082,18000328,TMIN,-23,,,E,
 436 | ITE00100554,18000329,TMAX,110,,,E,
 437 | ITE00100554,18000329,TMIN,85,,,E,
 438 | GM000010962,18000329,PRCP,0,,,E,
 439 | EZE00100082,18000329,TMAX,82,,,E,
 440 | EZE00100082,18000329,TMIN,4,,,E,
 441 | ITE00100554,18000330,TMAX,141,,,E,
 442 | ITE00100554,18000330,TMIN,85,,,E,
 443 | GM000010962,18000330,PRCP,0,,,E,
 444 | EZE00100082,18000330,TMAX,91,,,E,
 445 | EZE00100082,18000330,TMIN,10,,,E,
 446 | ITE00100554,18000331,TMAX,138,,,E,
 447 | ITE00100554,18000331,TMIN,75,,,E,
 448 | GM000010962,18000331,PRCP,0,,,E,
 449 | EZE00100082,18000331,TMAX,123,,,E,
 450 | EZE00100082,18000331,TMIN,11,,,E,
 451 | ITE00100554,18000401,TMAX,109,,,E,
 452 | ITE00100554,18000401,TMIN,100,,,E,
 453 | GM000010962,18000401,PRCP,0,,,E,
 454 | EZE00100082,18000401,TMAX,98,,,E,
 455 | EZE00100082,18000401,TMIN,50,,,E,
 456 | ITE00100554,18000402,TMAX,104,,,E,
 457 | ITE00100554,18000402,TMIN,98,,,E,
 458 | GM000010962,18000402,PRCP,9,,,E,
 459 | EZE00100082,18000402,TMAX,128,,,E,
 460 | EZE00100082,18000402,TMIN,59,,,E,
 461 | ITE00100554,18000403,TMAX,128,,,E,
 462 | ITE00100554,18000403,TMIN,75,,,E,
 463 | GM000010962,18000403,PRCP,0,,,E,
 464 | EZE00100082,18000403,TMAX,116,,,E,
 465 | EZE00100082,18000403,TMIN,61,,,E,
 466 | ITE00100554,18000404,TMAX,153,,,E,
 467 | ITE00100554,18000404,TMIN,75,,,E,
 468 | GM000010962,18000404,PRCP,0,,,E,
 469 | EZE00100082,18000404,TMAX,157,,,E,
 470 | EZE00100082,18000404,TMIN,69,,,E,
 471 | ITE00100554,18000405,TMAX,166,,,E,
 472 | ITE00100554,18000405,TMIN,84,,,E,
 473 | GM000010962,18000405,PRCP,0,,,E,
 474 | EZE00100082,18000405,TMAX,134,,,E,
 475 | EZE00100082,18000405,TMIN,65,,,E,
 476 | ITE00100554,18000406,TMAX,178,,,E,
 477 | ITE00100554,18000406,TMIN,96,,,E,
 478 | GM000010962,18000406,PRCP,0,,,E,
 479 | EZE00100082,18000406,TMAX,168,,,E,
 480 | EZE00100082,18000406,TMIN,95,,,E,
 481 | ITE00100554,18000407,TMAX,198,,,E,
 482 | ITE00100554,18000407,TMIN,99,,,E,
 483 | GM000010962,18000407,PRCP,0,,,E,
 484 | EZE00100082,18000407,TMAX,160,,,E,
 485 | EZE00100082,18000407,TMIN,74,,,E,
 486 | ITE00100554,18000408,TMAX,200,,,E,
 487 | ITE00100554,18000408,TMIN,109,,,E,
 488 | GM000010962,18000408,PRCP,0,,,E,
 489 | EZE00100082,18000408,TMAX,203,,,E,
 490 | EZE00100082,18000408,TMIN,75,,,E,
 491 | ITE00100554,18000409,TMAX,200,,,E,
 492 | ITE00100554,18000409,TMIN,148,,,E,
 493 | GM000010962,18000409,PRCP,0,,,E,
 494 | EZE00100082,18000409,TMAX,193,,,E,
 495 | EZE00100082,18000409,TMIN,105,,,E,
 496 | ITE00100554,18000410,TMAX,200,,,E,
 497 | ITE00100554,18000410,TMIN,129,,,E,
 498 | GM000010962,18000410,PRCP,0,,,E,
 499 | EZE00100082,18000410,TMAX,212,,,E,
 500 | EZE00100082,18000410,TMIN,125,,,E,
 501 | ITE00100554,18000411,TMAX,200,,,E,
 502 | ITE00100554,18000411,TMIN,141,,,E,
 503 | GM000010962,18000411,PRCP,0,,,E,
 504 | EZE00100082,18000411,TMAX,171,,,E,
 505 | EZE00100082,18000411,TMIN,95,,,E,
 506 | ITE00100554,18000412,TMAX,200,,,E,
 507 | ITE00100554,18000412,TMIN,116,,,E,
 508 | GM000010962,18000412,PRCP,10,,,E,
 509 | EZE00100082,18000412,TMAX,170,,,E,
 510 | EZE00100082,18000412,TMIN,55,,,E,
 511 | ITE00100554,18000413,TMAX,181,,,E,
 512 | ITE00100554,18000413,TMIN,129,,,E,
 513 | GM000010962,18000413,PRCP,40,,,E,
 514 | EZE00100082,18000413,TMAX,185,,,E,
 515 | EZE00100082,18000413,TMIN,99,,,E,
 516 | ITE00100554,18000414,TMAX,188,,,E,
 517 | ITE00100554,18000414,TMIN,91,,,E,
 518 | GM000010962,18000414,PRCP,2,,,E,
 519 | EZE00100082,18000414,TMAX,145,,,E,
 520 | EZE00100082,18000414,TMIN,87,,,E,
 521 | ITE00100554,18000415,TMAX,206,,,E,
 522 | ITE00100554,18000415,TMIN,116,,,E,
 523 | GM000010962,18000415,PRCP,0,,,E,
 524 | EZE00100082,18000415,TMAX,194,,,E,
 525 | EZE00100082,18000415,TMIN,109,,,E,
 526 | ITE00100554,18000416,TMAX,216,,,E,
 527 | ITE00100554,18000416,TMIN,129,,,E,
 528 | GM000010962,18000416,PRCP,0,,,E,
 529 | EZE00100082,18000416,TMAX,203,,,E,
 530 | EZE00100082,18000416,TMIN,102,,,E,
 531 | ITE00100554,18000417,TMAX,213,,,E,
 532 | ITE00100554,18000417,TMIN,129,,,E,
 533 | GM000010962,18000417,PRCP,0,,,E,
 534 | EZE00100082,18000417,TMAX,248,,,E,
 535 | EZE00100082,18000417,TMIN,110,,,E,
 536 | ITE00100554,18000418,TMAX,216,,,E,
 537 | ITE00100554,18000418,TMIN,134,,,E,
 538 | GM000010962,18000418,PRCP,0,,,E,
 539 | EZE00100082,18000418,TMAX,246,,,E,
 540 | EZE00100082,18000418,TMIN,130,,,E,
 541 | ITE00100554,18000419,TMAX,191,,,E,
 542 | ITE00100554,18000419,TMIN,138,,,E,
 543 | GM000010962,18000419,PRCP,5,,,E,
 544 | EZE00100082,18000419,TMAX,208,,,E,
 545 | EZE00100082,18000419,TMIN,146,,,E,
 546 | ITE00100554,18000420,TMAX,231,,,E,
 547 | ITE00100554,18000420,TMIN,150,,,E,
 548 | GM000010962,18000420,PRCP,34,,,E,
 549 | EZE00100082,18000420,TMAX,212,,,E,
 550 | EZE00100082,18000420,TMIN,125,,,E,
 551 | ITE00100554,18000421,TMAX,235,,,E,
 552 | ITE00100554,18000421,TMIN,154,,,E,
 553 | GM000010962,18000421,PRCP,2,,,E,
 554 | EZE00100082,18000421,TMAX,228,,,E,
 555 | EZE00100082,18000421,TMIN,153,,,E,
 556 | ITE00100554,18000422,TMAX,216,,,E,
 557 | ITE00100554,18000422,TMIN,166,,,E,
 558 | GM000010962,18000422,PRCP,0,,,E,
 559 | EZE00100082,18000422,TMAX,277,,,E,
 560 | EZE00100082,18000422,TMIN,157,,,E,
 561 | ITE00100554,18000423,TMAX,191,,,E,
 562 | ITE00100554,18000423,TMIN,166,,,E,
 563 | GM000010962,18000423,PRCP,0,,,E,
 564 | EZE00100082,18000423,TMAX,250,,,E,
 565 | EZE00100082,18000423,TMIN,185,,,E,
 566 | ITE00100554,18000424,TMAX,204,,,E,
 567 | ITE00100554,18000424,TMIN,146,,,E,
 568 | GM000010962,18000424,PRCP,0,,,E,
 569 | EZE00100082,18000424,TMAX,238,,,E,
 570 | EZE00100082,18000424,TMIN,177,,,E,
 571 | ITE00100554,18000425,TMAX,163,,,E,
 572 | ITE00100554,18000425,TMIN,150,,,E,
 573 | GM000010962,18000425,PRCP,0,,,E,
 574 | EZE00100082,18000425,TMAX,230,,,E,
 575 | EZE00100082,18000425,TMIN,166,,,E,
 576 | ITE00100554,18000426,TMAX,179,,,E,
 577 | ITE00100554,18000426,TMIN,154,,,E,
 578 | GM000010962,18000426,PRCP,0,,,E,
 579 | EZE00100082,18000426,TMAX,258,,,E,
 580 | EZE00100082,18000426,TMIN,158,,,E,
 581 | ITE00100554,18000427,TMAX,204,,,E,
 582 | ITE00100554,18000427,TMIN,154,,,E,
 583 | GM000010962,18000427,PRCP,0,,,E,
 584 | EZE00100082,18000427,TMAX,279,,,E,
 585 | EZE00100082,18000427,TMIN,160,,,E,
 586 | ITE00100554,18000428,TMAX,223,,,E,
 587 | ITE00100554,18000428,TMIN,159,,,E,
 588 | GM000010962,18000428,PRCP,0,,,E,
 589 | EZE00100082,18000428,TMAX,259,,,E,
 590 | EZE00100082,18000428,TMIN,180,,,E,
 591 | ITE00100554,18000429,TMAX,225,,,E,
 592 | ITE00100554,18000429,TMIN,169,,,E,
 593 | GM000010962,18000429,PRCP,0,,,E,
 594 | EZE00100082,18000429,TMAX,286,,,E,
 595 | EZE00100082,18000429,TMIN,166,,,E,
 596 | ITE00100554,18000430,TMAX,206,,,E,
 597 | ITE00100554,18000430,TMIN,159,,,E,
 598 | GM000010962,18000430,PRCP,0,,,E,
 599 | EZE00100082,18000430,TMAX,273,,,E,
 600 | EZE00100082,18000430,TMIN,147,,,E,
 601 | ITE00100554,18000501,TMAX,206,,,E,
 602 | ITE00100554,18000501,TMIN,160,,,E,
 603 | GM000010962,18000501,PRCP,97,,,E,
 604 | EZE00100082,18000501,TMAX,183,,,E,
 605 | EZE00100082,18000501,TMIN,127,,,E,
 606 | ITE00100554,18000502,TMAX,223,,,E,
 607 | ITE00100554,18000502,TMIN,160,,,E,
 608 | GM000010962,18000502,PRCP,3,,,E,
 609 | EZE00100082,18000502,TMAX,226,,,E,
 610 | EZE00100082,18000502,TMIN,139,,,E,
 611 | ITE00100554,18000503,TMAX,235,,,E,
 612 | ITE00100554,18000503,TMIN,154,,,E,
 613 | GM000010962,18000503,PRCP,0,,,E,
 614 | EZE00100082,18000503,TMAX,240,,,E,
 615 | EZE00100082,18000503,TMIN,164,,,E,
 616 | ITE00100554,18000504,TMAX,238,,,E,
 617 | ITE00100554,18000504,TMIN,156,,,E,
 618 | GM000010962,18000504,PRCP,0,,,E,
 619 | EZE00100082,18000504,TMAX,231,,,E,
 620 | EZE00100082,18000504,TMIN,152,,,E,
 621 | ITE00100554,18000505,TMAX,225,,,E,
 622 | ITE00100554,18000505,TMIN,160,,,E,
 623 | GM000010962,18000505,PRCP,0,,,E,
 624 | EZE00100082,18000505,TMAX,217,,,E,
 625 | EZE00100082,18000505,TMIN,160,,,E,
 626 | ITE00100554,18000506,TMAX,175,,,E,
 627 | ITE00100554,18000506,TMIN,140,,,E,
 628 | GM000010962,18000506,PRCP,0,,,E,
 629 | EZE00100082,18000506,TMAX,214,,,E,
 630 | EZE00100082,18000506,TMIN,136,,,E,
 631 | ITE00100554,18000507,TMAX,188,,,E,
 632 | ITE00100554,18000507,TMIN,96,,,E,
 633 | GM000010962,18000507,PRCP,0,,,E,
 634 | EZE00100082,18000507,TMAX,231,,,E,
 635 | EZE00100082,18000507,TMIN,116,,,E,
 636 | ITE00100554,18000508,TMAX,213,,,E,
 637 | ITE00100554,18000508,TMIN,121,,,E,
 638 | GM000010962,18000508,PRCP,0,,,E,
 639 | EZE00100082,18000508,TMAX,240,,,E,
 640 | EZE00100082,18000508,TMIN,130,,,E,
 641 | ITE00100554,18000509,TMAX,225,,,E,
 642 | ITE00100554,18000509,TMIN,134,,,E,
 643 | GM000010962,18000509,PRCP,0,,,E,
 644 | EZE00100082,18000509,TMAX,245,,,E,
 645 | EZE00100082,18000509,TMIN,151,,,E,
 646 | ITE00100554,18000510,TMAX,188,,,E,
 647 | ITE00100554,18000510,TMIN,154,,,E,
 648 | GM000010962,18000510,PRCP,0,,,E,
 649 | EZE00100082,18000510,TMAX,241,,,E,
 650 | EZE00100082,18000510,TMIN,149,,,E,
 651 | ITE00100554,18000511,TMAX,210,,,E,
 652 | ITE00100554,18000511,TMIN,154,,,E,
 653 | GM000010962,18000511,PRCP,11,,,E,
 654 | EZE00100082,18000511,TMAX,162,,,E,
 655 | EZE00100082,18000511,TMIN,103,,,E,
 656 | ITE00100554,18000512,TMAX,204,,,E,
 657 | ITE00100554,18000512,TMIN,150,,,E,
 658 | GM000010962,18000512,PRCP,7,,,E,
 659 | EZE00100082,18000512,TMAX,162,,,E,
 660 | EZE00100082,18000512,TMIN,100,,,E,
 661 | ITE00100554,18000513,TMAX,188,,,E,
 662 | ITE00100554,18000513,TMIN,154,,,E,
 663 | GM000010962,18000513,PRCP,25,,,E,
 664 | EZE00100082,18000513,TMAX,197,,,E,
 665 | EZE00100082,18000513,TMIN,122,,,E,
 666 | ITE00100554,18000514,TMAX,200,,,E,
 667 | ITE00100554,18000514,TMIN,134,,,E,
 668 | GM000010962,18000514,PRCP,35,,,E,
 669 | EZE00100082,18000514,TMAX,209,,,E,
 670 | EZE00100082,18000514,TMIN,125,,,E,
 671 | ITE00100554,18000515,TMAX,213,,,E,
 672 | ITE00100554,18000515,TMIN,135,,,E,
 673 | GM000010962,18000515,PRCP,7,,,E,
 674 | EZE00100082,18000515,TMAX,161,,,E,
 675 | EZE00100082,18000515,TMIN,116,,,E,
 676 | ITE00100554,18000516,TMAX,213,,,E,
 677 | ITE00100554,18000516,TMIN,135,,,E,
 678 | GM000010962,18000516,PRCP,279,,,E,
 679 | EZE00100082,18000516,TMAX,188,,,E,
 680 | EZE00100082,18000516,TMIN,129,,,E,
 681 | ITE00100554,18000517,TMAX,209,,,E,
 682 | ITE00100554,18000517,TMIN,160,,,E,
 683 | GM000010962,18000517,PRCP,0,,,E,
 684 | EZE00100082,18000517,TMAX,220,,,E,
 685 | EZE00100082,18000517,TMIN,124,,,E,
 686 | ITE00100554,18000518,TMAX,213,,,E,
 687 | ITE00100554,18000518,TMIN,146,,,E,
 688 | GM000010962,18000518,PRCP,43,,,E,
 689 | EZE00100082,18000518,TMAX,186,,,E,
 690 | EZE00100082,18000518,TMIN,119,,,E,
 691 | ITE00100554,18000519,TMAX,200,,,E,
 692 | ITE00100554,18000519,TMIN,135,,,E,
 693 | GM000010962,18000519,PRCP,0,,,E,
 694 | EZE00100082,18000519,TMAX,172,,,E,
 695 | EZE00100082,18000519,TMIN,105,,,E,
 696 | ITE00100554,18000520,TMAX,225,,,E,
 697 | ITE00100554,18000520,TMIN,138,,,E,
 698 | GM000010962,18000520,PRCP,0,,,E,
 699 | EZE00100082,18000520,TMAX,225,,,E,
 700 | EZE00100082,18000520,TMIN,115,,,E,
 701 | ITE00100554,18000521,TMAX,238,,,E,
 702 | ITE00100554,18000521,TMIN,179,,,E,
 703 | GM000010962,18000521,PRCP,0,,,E,
 704 | EZE00100082,18000521,TMAX,247,,,E,
 705 | EZE00100082,18000521,TMIN,136,,,E,
 706 | ITE00100554,18000522,TMAX,263,,,E,
 707 | ITE00100554,18000522,TMIN,166,,,E,
 708 | GM000010962,18000522,PRCP,43,,,E,
 709 | EZE00100082,18000522,TMAX,262,,,E,
 710 | EZE00100082,18000522,TMIN,157,,,E,
 711 | ITE00100554,18000523,TMAX,250,,,E,
 712 | ITE00100554,18000523,TMIN,188,,,E,
 713 | GM000010962,18000523,PRCP,71,,,E,
 714 | EZE00100082,18000523,TMAX,270,,,E,
 715 | EZE00100082,18000523,TMIN,183,,,E,
 716 | ITE00100554,18000524,TMAX,225,,,E,
 717 | ITE00100554,18000524,TMIN,185,,,E,
 718 | GM000010962,18000524,PRCP,0,,,E,
 719 | EZE00100082,18000524,TMAX,282,,,E,
 720 | EZE00100082,18000524,TMIN,178,,,E,
 721 | ITE00100554,18000525,TMAX,238,,,E,
 722 | ITE00100554,18000525,TMIN,181,,,E,
 723 | GM000010962,18000525,PRCP,305,,,E,
 724 | EZE00100082,18000525,TMAX,232,,,E,
 725 | EZE00100082,18000525,TMIN,174,,,E,
 726 | ITE00100554,18000526,TMAX,263,,,E,
 727 | ITE00100554,18000526,TMIN,198,,,E,
 728 | GM000010962,18000526,PRCP,169,,,E,
 729 | EZE00100082,18000526,TMAX,226,,,E,
 730 | EZE00100082,18000526,TMIN,160,,,E,
 731 | ITE00100554,18000527,TMAX,269,,,E,
 732 | ITE00100554,18000527,TMIN,210,,,E,
 733 | GM000010962,18000527,PRCP,24,,,E,
 734 | EZE00100082,18000527,TMAX,246,,,E,
 735 | EZE00100082,18000527,TMIN,173,,,E,
 736 | ITE00100554,18000528,TMAX,244,,,E,
 737 | ITE00100554,18000528,TMIN,191,,,E,
 738 | GM000010962,18000528,PRCP,2,,,E,
 739 | EZE00100082,18000528,TMAX,261,,,E,
 740 | EZE00100082,18000528,TMIN,189,,,E,
 741 | ITE00100554,18000529,TMAX,216,,,E,
 742 | ITE00100554,18000529,TMIN,191,,,E,
 743 | GM000010962,18000529,PRCP,123,,,E,
 744 | EZE00100082,18000529,TMAX,258,,,E,
 745 | EZE00100082,18000529,TMIN,194,,,E,
 746 | ITE00100554,18000530,TMAX,259,,,E,
 747 | ITE00100554,18000530,TMIN,196,,,E,
 748 | GM000010962,18000530,PRCP,97,,,E,
 749 | EZE00100082,18000530,TMAX,238,,,E,
 750 | EZE00100082,18000530,TMIN,183,,,E,
 751 | ITE00100554,18000531,TMAX,254,,,E,
 752 | ITE00100554,18000531,TMIN,196,,,E,
 753 | GM000010962,18000531,PRCP,75,,,E,
 754 | EZE00100082,18000531,TMAX,210,,,E,
 755 | EZE00100082,18000531,TMIN,170,,,E,
 756 | ITE00100554,18000601,TMAX,204,,,E,
 757 | ITE00100554,18000601,TMIN,191,,,E,
 758 | GM000010962,18000601,PRCP,102,,,E,
 759 | EZE00100082,18000601,TMAX,191,,,E,
 760 | EZE00100082,18000601,TMIN,157,,,E,
 761 | ITE00100554,18000602,TMAX,216,,,E,
 762 | ITE00100554,18000602,TMIN,138,,,E,
 763 | GM000010962,18000602,PRCP,45,,,E,
 764 | EZE00100082,18000602,TMAX,193,,,E,
 765 | EZE00100082,18000602,TMIN,132,,,E,
 766 | ITE00100554,18000603,TMAX,213,,,E,
 767 | ITE00100554,18000603,TMIN,138,,,E,
 768 | GM000010962,18000603,PRCP,0,,,E,
 769 | EZE00100082,18000603,TMAX,192,,,E,
 770 | EZE00100082,18000603,TMIN,144,,,E,
 771 | ITE00100554,18000604,TMAX,225,,,E,
 772 | ITE00100554,18000604,TMIN,156,,,E,
 773 | GM000010962,18000604,PRCP,11,,,E,
 774 | EZE00100082,18000604,TMAX,216,,,E,
 775 | EZE00100082,18000604,TMIN,141,,,E,
 776 | ITE00100554,18000605,TMAX,256,,,E,
 777 | ITE00100554,18000605,TMIN,173,,,E,
 778 | GM000010962,18000605,PRCP,0,,,E,
 779 | EZE00100082,18000605,TMAX,226,,,E,
 780 | EZE00100082,18000605,TMIN,147,,,E,
 781 | ITE00100554,18000606,TMAX,250,,,E,
 782 | ITE00100554,18000606,TMIN,184,,,E,
 783 | GM000010962,18000606,PRCP,27,,,E,
 784 | EZE00100082,18000606,TMAX,227,,,E,
 785 | EZE00100082,18000606,TMIN,177,,,E,
 786 | ITE00100554,18000607,TMAX,198,,,E,
 787 | ITE00100554,18000607,TMIN,173,,,E,
 788 | GM000010962,18000607,PRCP,23,,,E,
 789 | EZE00100082,18000607,TMAX,219,,,E,
 790 | EZE00100082,18000607,TMIN,133,,,E,
 791 | ITE00100554,18000608,TMAX,191,,,E,
 792 | ITE00100554,18000608,TMIN,169,,,E,
 793 | GM000010962,18000608,PRCP,297,,,E,
 794 | EZE00100082,18000608,TMAX,164,,,E,
 795 | EZE00100082,18000608,TMIN,117,,,E,
 796 | ITE00100554,18000609,TMAX,223,,,E,
 797 | ITE00100554,18000609,TMIN,166,,,E,
 798 | GM000010962,18000609,PRCP,2,,,E,
 799 | EZE00100082,18000609,TMAX,191,,,E,
 800 | EZE00100082,18000609,TMIN,119,,,E,
 801 | ITE00100554,18000610,TMAX,248,,,E,
 802 | ITE00100554,18000610,TMIN,166,,,E,
 803 | GM000010962,18000610,PRCP,0,,,E,
 804 | EZE00100082,18000610,TMAX,191,,,E,
 805 | EZE00100082,18000610,TMIN,129,,,E,
 806 | ITE00100554,18000611,TMAX,229,,,E,
 807 | ITE00100554,18000611,TMIN,169,,,E,
 808 | GM000010962,18000611,PRCP,40,,,E,
 809 | EZE00100082,18000611,TMAX,185,,,E,
 810 | EZE00100082,18000611,TMIN,104,,,E,
 811 | ITE00100554,18000612,TMAX,206,,,E,
 812 | ITE00100554,18000612,TMIN,175,,,E,
 813 | GM000010962,18000612,PRCP,10,,,E,
 814 | EZE00100082,18000612,TMAX,190,,,E,
 815 | EZE00100082,18000612,TMIN,100,,,E,
 816 | ITE00100554,18000613,TMAX,229,,,E,
 817 | ITE00100554,18000613,TMIN,171,,,E,
 818 | GM000010962,18000613,PRCP,51,,,E,
 819 | EZE00100082,18000613,TMAX,198,,,E,
 820 | EZE00100082,18000613,TMIN,115,,,E,
 821 | ITE00100554,18000614,TMAX,216,,,E,
 822 | ITE00100554,18000614,TMIN,166,,,E,
 823 | GM000010962,18000614,PRCP,10,,,E,
 824 | EZE00100082,18000614,TMAX,212,,,E,
 825 | EZE00100082,18000614,TMIN,126,,,E,
 826 | ITE00100554,18000615,TMAX,216,,,E,
 827 | ITE00100554,18000615,TMIN,141,,,E,
 828 | GM000010962,18000615,PRCP,7,,,E,
 829 | EZE00100082,18000615,TMAX,148,,,E,
 830 | EZE00100082,18000615,TMIN,90,,,E,
 831 | ITE00100554,18000616,TMAX,216,,,E,
 832 | ITE00100554,18000616,TMIN,141,,,E,
 833 | GM000010962,18000616,PRCP,16,,,E,
 834 | EZE00100082,18000616,TMAX,139,,,E,
 835 | EZE00100082,18000616,TMIN,84,,,E,
 836 | ITE00100554,18000617,TMAX,225,,,E,
 837 | ITE00100554,18000617,TMIN,141,,,E,
 838 | GM000010962,18000617,PRCP,12,,,E,
 839 | EZE00100082,18000617,TMAX,131,,,E,
 840 | EZE00100082,18000617,TMIN,82,,,E,
 841 | ITE00100554,18000618,TMAX,235,,,E,
 842 | ITE00100554,18000618,TMIN,146,,,E,
 843 | GM000010962,18000618,PRCP,0,,,E,
 844 | EZE00100082,18000618,TMAX,140,,,E,
 845 | EZE00100082,18000618,TMIN,87,,,E,
 846 | ITE00100554,18000619,TMAX,235,,,E,
 847 | ITE00100554,18000619,TMIN,148,,,E,
 848 | GM000010962,18000619,PRCP,63,,,E,
 849 | EZE00100082,18000619,TMAX,164,,,E,
 850 | EZE00100082,18000619,TMIN,98,,,E,
 851 | ITE00100554,18000620,TMAX,254,,,E,
 852 | ITE00100554,18000620,TMIN,146,,,E,
 853 | GM000010962,18000620,PRCP,17,,,E,
 854 | EZE00100082,18000620,TMAX,210,,,E,
 855 | EZE00100082,18000620,TMIN,88,,,E,
 856 | ITE00100554,18000621,TMAX,259,,,E,
 857 | ITE00100554,18000621,TMIN,173,,,E,
 858 | GM000010962,18000621,PRCP,2,,,E,
 859 | EZE00100082,18000621,TMAX,195,,,E,
 860 | EZE00100082,18000621,TMIN,156,,,E,
 861 | ITE00100554,18000622,TMAX,213,,,E,
 862 | ITE00100554,18000622,TMIN,204,,,E,
 863 | GM000010962,18000622,PRCP,111,,,E,
 864 | EZE00100082,18000622,TMAX,192,,,E,
 865 | EZE00100082,18000622,TMIN,134,,,E,
 866 | ITE00100554,18000623,TMAX,241,,,E,
 867 | ITE00100554,18000623,TMIN,154,,,E,
 868 | GM000010962,18000623,PRCP,27,,,E,
 869 | EZE00100082,18000623,TMAX,182,,,E,
 870 | EZE00100082,18000623,TMIN,118,,,E,
 871 | ITE00100554,18000624,TMAX,241,,,E,
 872 | ITE00100554,18000624,TMIN,179,,,E,
 873 | GM000010962,18000624,PRCP,0,,,E,
 874 | EZE00100082,18000624,TMAX,194,,,E,
 875 | EZE00100082,18000624,TMIN,115,,,E,
 876 | ITE00100554,18000625,TMAX,254,,,E,
 877 | ITE00100554,18000625,TMIN,184,,,E,
 878 | GM000010962,18000625,PRCP,0,,,E,
 879 | EZE00100082,18000625,TMAX,217,,,E,
 880 | EZE00100082,18000625,TMIN,100,,,E,
 881 | ITE00100554,18000626,TMAX,263,,,E,
 882 | ITE00100554,18000626,TMIN,184,,,E,
 883 | GM000010962,18000626,PRCP,0,,,E,
 884 | EZE00100082,18000626,TMAX,233,,,E,
 885 | EZE00100082,18000626,TMIN,131,,,E,
 886 | ITE00100554,18000627,TMAX,275,,,E,
 887 | ITE00100554,18000627,TMIN,204,,,E,
 888 | GM000010962,18000627,PRCP,0,,,E,
 889 | EZE00100082,18000627,TMAX,234,,,E,
 890 | EZE00100082,18000627,TMIN,161,,,E,
 891 | ITE00100554,18000628,TMAX,288,,,E,
 892 | ITE00100554,18000628,TMIN,213,,,E,
 893 | GM000010962,18000628,PRCP,12,,,E,
 894 | EZE00100082,18000628,TMAX,227,,,E,
 895 | EZE00100082,18000628,TMIN,140,,,E,
 896 | ITE00100554,18000629,TMAX,265,,,E,
 897 | ITE00100554,18000629,TMIN,198,,,E,
 898 | GM000010962,18000629,PRCP,0,,,E,
 899 | EZE00100082,18000629,TMAX,250,,,E,
 900 | EZE00100082,18000629,TMIN,137,,,E,
 901 | ITE00100554,18000630,TMAX,279,,,E,
 902 | ITE00100554,18000630,TMIN,209,,,E,
 903 | GM000010962,18000630,PRCP,88,,,E,
 904 | EZE00100082,18000630,TMAX,214,,,E,
 905 | EZE00100082,18000630,TMIN,155,,,E,
 906 | ITE00100554,18000701,TMAX,275,,,E,
 907 | ITE00100554,18000701,TMIN,213,,,E,
 908 | GM000010962,18000701,PRCP,32,,,E,
 909 | EZE00100082,18000701,TMAX,180,,,E,
 910 | EZE00100082,18000701,TMIN,128,,,E,
 911 | ITE00100554,18000702,TMAX,241,,,E,
 912 | ITE00100554,18000702,TMIN,185,,,E,
 913 | GM000010962,18000702,PRCP,0,,,E,
 914 | EZE00100082,18000702,TMAX,193,,,E,
 915 | EZE00100082,18000702,TMIN,135,,,E,
 916 | ITE00100554,18000703,TMAX,254,,,E,
 917 | ITE00100554,18000703,TMIN,200,,,E,
 918 | GM000010962,18000703,PRCP,0,,,E,
 919 | EZE00100082,18000703,TMAX,240,,,E,
 920 | EZE00100082,18000703,TMIN,134,,,E,
 921 | ITE00100554,18000704,TMAX,288,,,E,
 922 | ITE00100554,18000704,TMIN,200,,,E,
 923 | GM000010962,18000704,PRCP,33,,,E,
 924 | EZE00100082,18000704,TMAX,216,,,E,
 925 | EZE00100082,18000704,TMIN,144,,,E,
 926 | ITE00100554,18000705,TMAX,275,,,E,
 927 | ITE00100554,18000705,TMIN,219,,,E,
 928 | GM000010962,18000705,PRCP,0,,,E,
 929 | EZE00100082,18000705,TMAX,281,,,E,
 930 | EZE00100082,18000705,TMIN,147,,,E,
 931 | ITE00100554,18000706,TMAX,288,,,E,
 932 | ITE00100554,18000706,TMIN,213,,,E,
 933 | GM000010962,18000706,PRCP,0,,,E,
 934 | EZE00100082,18000706,TMAX,285,,,E,
 935 | EZE00100082,18000706,TMIN,188,,,E,
 936 | ITE00100554,18000707,TMAX,278,,,E,
 937 | ITE00100554,18000707,TMIN,221,,,E,
 938 | GM000010962,18000707,PRCP,0,,,E,
 939 | EZE00100082,18000707,TMAX,286,,,E,
 940 | EZE00100082,18000707,TMIN,180,,,E,
 941 | ITE00100554,18000708,TMAX,300,,,E,
 942 | ITE00100554,18000708,TMIN,209,,,E,
 943 | GM000010962,18000708,PRCP,43,,,E,
 944 | EZE00100082,18000708,TMAX,293,,,E,
 945 | EZE00100082,18000708,TMIN,180,,,E,
 946 | ITE00100554,18000709,TMAX,304,,,E,
 947 | ITE00100554,18000709,TMIN,225,,,E,
 948 | GM000010962,18000709,PRCP,0,,,E,
 949 | EZE00100082,18000709,TMAX,306,,,E,
 950 | EZE00100082,18000709,TMIN,204,,,E,
 951 | ITE00100554,18000710,TMAX,319,,,E,
 952 | ITE00100554,18000710,TMIN,235,,,E,
 953 | GM000010962,18000710,PRCP,117,,,E,
 954 | EZE00100082,18000710,TMAX,290,,,E,
 955 | EZE00100082,18000710,TMIN,195,,,E,
 956 | ITE00100554,18000711,TMAX,304,,,E,
 957 | ITE00100554,18000711,TMIN,238,,,E,
 958 | GM000010962,18000711,PRCP,86,,,E,
 959 | EZE00100082,18000711,TMAX,195,,,E,
 960 | EZE00100082,18000711,TMIN,159,,,E,
 961 | ITE00100554,18000712,TMAX,285,,,E,
 962 | ITE00100554,18000712,TMIN,241,,,E,
 963 | GM000010962,18000712,PRCP,0,,,E,
 964 | EZE00100082,18000712,TMAX,244,,,E,
 965 | EZE00100082,18000712,TMIN,160,,,E,
 966 | ITE00100554,18000713,TMAX,300,,,E,
 967 | ITE00100554,18000713,TMIN,231,,,E,
 968 | GM000010962,18000713,PRCP,0,,,E,
 969 | EZE00100082,18000713,TMAX,217,,,E,
 970 | EZE00100082,18000713,TMIN,172,,,E,
 971 | ITE00100554,18000714,TMAX,300,,,E,
 972 | ITE00100554,18000714,TMIN,225,,,E,
 973 | GM000010962,18000714,PRCP,0,,,E,
 974 | EZE00100082,18000714,TMAX,186,,,E,
 975 | EZE00100082,18000714,TMIN,144,,,E,
 976 | ITE00100554,18000715,TMAX,266,,,E,
 977 | ITE00100554,18000715,TMIN,225,,,E,
 978 | GM000010962,18000715,PRCP,2,,,E,
 979 | EZE00100082,18000715,TMAX,192,,,E,
 980 | EZE00100082,18000715,TMIN,124,,,E,
 981 | ITE00100554,18000716,TMAX,248,,,E,
 982 | ITE00100554,18000716,TMIN,204,,,E,
 983 | GM000010962,18000716,PRCP,0,,,E,
 984 | EZE00100082,18000716,TMAX,185,,,E,
 985 | EZE00100082,18000716,TMIN,133,,,E,
 986 | ITE00100554,18000717,TMAX,275,,,E,
 987 | ITE00100554,18000717,TMIN,209,,,E,
 988 | GM000010962,18000717,PRCP,0,,,E,
 989 | EZE00100082,18000717,TMAX,204,,,E,
 990 | EZE00100082,18000717,TMIN,140,,,E,
 991 | ITE00100554,18000718,TMAX,294,,,E,
 992 | ITE00100554,18000718,TMIN,213,,,E,
 993 | GM000010962,18000718,PRCP,0,,,E,
 994 | EZE00100082,18000718,TMAX,193,,,E,
 995 | EZE00100082,18000718,TMIN,142,,,E,
 996 | ITE00100554,18000719,TMAX,284,,,E,
 997 | ITE00100554,18000719,TMIN,225,,,E,
 998 | GM000010962,18000719,PRCP,0,,,E,
 999 | EZE00100082,18000719,TMAX,200,,,E,
1000 | EZE00100082,18000719,TMIN,136,,,E,
1001 | ITE00100554,18000720,TMAX,263,,,E,
1002 | ITE00100554,18000720,TMIN,191,,,E,
1003 | GM000010962,18000720,PRCP,0,,,E,
1004 | EZE00100082,18000720,TMAX,204,,,E,
1005 | EZE00100082,18000720,TMIN,132,,,E,
1006 | ITE00100554,18000721,TMAX,285,,,E,
1007 | ITE00100554,18000721,TMIN,191,,,E,
1008 | GM000010962,18000721,PRCP,2,,,E,
1009 | EZE00100082,18000721,TMAX,170,,,E,
1010 | EZE00100082,18000721,TMIN,124,,,E,
1011 | ITE00100554,18000722,TMAX,266,,,E,
1012 | ITE00100554,18000722,TMIN,213,,,E,
1013 | GM000010962,18000722,PRCP,80,,,E,
1014 | EZE00100082,18000722,TMAX,178,,,E,
1015 | EZE00100082,18000722,TMIN,130,,,E,
1016 | ITE00100554,18000723,TMAX,250,,,E,
1017 | ITE00100554,18000723,TMIN,163,,,E,
1018 | GM000010962,18000723,PRCP,40,,,E,
1019 | EZE00100082,18000723,TMAX,190,,,E,
1020 | EZE00100082,18000723,TMIN,143,,,E,
1021 | ITE00100554,18000724,TMAX,254,,,E,
1022 | ITE00100554,18000724,TMIN,171,,,E,
1023 | GM000010962,18000724,PRCP,11,,,E,
1024 | EZE00100082,18000724,TMAX,213,,,E,
1025 | EZE00100082,18000724,TMIN,155,,,E,
1026 | ITE00100554,18000725,TMAX,269,,,E,
1027 | ITE00100554,18000725,TMIN,191,,,E,
1028 | GM000010962,18000725,PRCP,0,,,E,
1029 | EZE00100082,18000725,TMAX,238,,,E,
1030 | EZE00100082,18000725,TMIN,152,,,E,
1031 | ITE00100554,18000726,TMAX,281,,,E,
1032 | ITE00100554,18000726,TMIN,191,,,E,
1033 | GM000010962,18000726,PRCP,0,,,E,
1034 | EZE00100082,18000726,TMAX,220,,,E,
1035 | EZE00100082,18000726,TMIN,144,,,E,
1036 | ITE00100554,18000727,TMAX,271,,,E,
1037 | ITE00100554,18000727,TMIN,206,,,E,
1038 | GM000010962,18000727,PRCP,0,,,E,
1039 | EZE00100082,18000727,TMAX,222,,,E,
1040 | EZE00100082,18000727,TMIN,169,,,E,
1041 | ITE00100554,18000728,TMAX,269,,,E,
1042 | ITE00100554,18000728,TMIN,216,,,E,
1043 | GM000010962,18000728,PRCP,0,,,E,
1044 | EZE00100082,18000728,TMAX,233,,,E,
1045 | EZE00100082,18000728,TMIN,144,,,E,
1046 | ITE00100554,18000729,TMAX,241,,,E,
1047 | ITE00100554,18000729,TMIN,200,,,E,
1048 | GM000010962,18000729,PRCP,0,,,E,
1049 | EZE00100082,18000729,TMAX,230,,,E,
1050 | EZE00100082,18000729,TMIN,150,,,E,
1051 | ITE00100554,18000730,TMAX,241,,,E,
1052 | ITE00100554,18000730,TMIN,200,,,E,
1053 | GM000010962,18000730,PRCP,0,,,E,
1054 | EZE00100082,18000730,TMAX,230,,,E,
1055 | EZE00100082,18000730,TMIN,120,,,E,
1056 | ITE00100554,18000731,TMAX,271,,,E,
1057 | ITE00100554,18000731,TMIN,188,,,E,
1058 | GM000010962,18000731,PRCP,0,,,E,
1059 | EZE00100082,18000731,TMAX,227,,,E,
1060 | EZE00100082,18000731,TMIN,137,,,E,
1061 | ITE00100554,18000801,TMAX,250,,,E,
1062 | ITE00100554,18000801,TMIN,200,,,E,
1063 | GM000010962,18000801,PRCP,0,,,E,
1064 | EZE00100082,18000801,TMAX,242,,,E,
1065 | EZE00100082,18000801,TMIN,140,,,E,
1066 | ITE00100554,18000802,TMAX,263,,,E,
1067 | ITE00100554,18000802,TMIN,188,,,E,
1068 | GM000010962,18000802,PRCP,0,,,E,
1069 | EZE00100082,18000802,TMAX,250,,,E,
1070 | EZE00100082,18000802,TMIN,154,,,E,
1071 | ITE00100554,18000803,TMAX,275,,,E,
1072 | ITE00100554,18000803,TMIN,200,,,E,
1073 | GM000010962,18000803,PRCP,0,,,E,
1074 | EZE00100082,18000803,TMAX,281,,,E,
1075 | EZE00100082,18000803,TMIN,183,,,E,
1076 | ITE00100554,18000804,TMAX,288,,,E,
1077 | ITE00100554,18000804,TMIN,200,,,E,
1078 | GM000010962,18000804,PRCP,0,,,E,
1079 | EZE00100082,18000804,TMAX,316,,,E,
1080 | EZE00100082,18000804,TMIN,192,,,E,
1081 | ITE00100554,18000805,TMAX,309,,,E,
1082 | ITE00100554,18000805,TMIN,210,,,E,
1083 | GM000010962,18000805,PRCP,0,,,E,
1084 | EZE00100082,18000805,TMAX,248,,,E,
1085 | EZE00100082,18000805,TMIN,168,,,E,
1086 | ITE00100554,18000806,TMAX,288,,,E,
1087 | ITE00100554,18000806,TMIN,213,,,E,
1088 | GM000010962,18000806,PRCP,0,,,E,
1089 | EZE00100082,18000806,TMAX,216,,,E,
1090 | EZE00100082,18000806,TMIN,138,,,E,
1091 | ITE00100554,18000807,TMAX,298,,,E,
1092 | ITE00100554,18000807,TMIN,200,,,E,
1093 | GM000010962,18000807,PRCP,0,,,E,
1094 | EZE00100082,18000807,TMAX,210,,,E,
1095 | EZE00100082,18000807,TMIN,141,,,E,
1096 | ITE00100554,18000808,TMAX,223,,,E,
1097 | ITE00100554,18000808,TMIN,143,,,E,
1098 | GM000010962,18000808,PRCP,0,,,E,
1099 | EZE00100082,18000808,TMAX,193,,,E,
1100 | EZE00100082,18000808,TMIN,136,,,E,
1101 | ITE00100554,18000809,TMAX,240,,,E,
1102 | ITE00100554,18000809,TMIN,144,,,E,
1103 | GM000010962,18000809,PRCP,9,,,E,
1104 | EZE00100082,18000809,TMAX,214,,,E,
1105 | EZE00100082,18000809,TMIN,117,,,E,
1106 | ITE00100554,18000810,TMAX,246,,,E,
1107 | ITE00100554,18000810,TMIN,159,,,E,
1108 | GM000010962,18000810,PRCP,0,,,E,
1109 | EZE00100082,18000810,TMAX,251,,,E,
1110 | EZE00100082,18000810,TMIN,155,,,E,
1111 | ITE00100554,18000811,TMAX,271,,,E,
1112 | ITE00100554,18000811,TMIN,166,,,E,
1113 | GM000010962,18000811,PRCP,0,,,E,
1114 | EZE00100082,18000811,TMAX,246,,,E,
1115 | EZE00100082,18000811,TMIN,155,,,E,
1116 | ITE00100554,18000812,TMAX,259,,,E,
1117 | ITE00100554,18000812,TMIN,184,,,E,
1118 | GM000010962,18000812,PRCP,0,,,E,
1119 | EZE00100082,18000812,TMAX,262,,,E,
1120 | EZE00100082,18000812,TMIN,162,,,E,
1121 | ITE00100554,18000813,TMAX,281,,,E,
1122 | ITE00100554,18000813,TMIN,204,,,E,
1123 | GM000010962,18000813,PRCP,0,,,E,
1124 | EZE00100082,18000813,TMAX,287,,,E,
1125 | EZE00100082,18000813,TMIN,165,,,E,
1126 | ITE00100554,18000814,TMAX,284,,,E,
1127 | ITE00100554,18000814,TMIN,221,,,E,
1128 | GM000010962,18000814,PRCP,0,,,E,
1129 | EZE00100082,18000814,TMAX,306,,,E,
1130 | EZE00100082,18000814,TMIN,180,,,E,
1131 | ITE00100554,18000815,TMAX,298,,,E,
1132 | ITE00100554,18000815,TMIN,216,,,E,
1133 | GM000010962,18000815,PRCP,0,,,E,
1134 | EZE00100082,18000815,TMAX,307,,,E,
1135 | EZE00100082,18000815,TMIN,181,,,E,
1136 | ITE00100554,18000816,TMAX,304,,,E,
1137 | ITE00100554,18000816,TMIN,216,,,E,
1138 | GM000010962,18000816,PRCP,0,,,E,
1139 | EZE00100082,18000816,TMAX,304,,,E,
1140 | EZE00100082,18000816,TMIN,198,,,E,
1141 | ITE00100554,18000817,TMAX,309,,,E,
1142 | ITE00100554,18000817,TMIN,216,,,E,
1143 | GM000010962,18000817,PRCP,0,,,E,
1144 | EZE00100082,18000817,TMAX,275,,,E,
1145 | EZE00100082,18000817,TMIN,178,,,E,
1146 | ITE00100554,18000818,TMAX,313,,,E,
1147 | ITE00100554,18000818,TMIN,221,,,E,
1148 | GM000010962,18000818,PRCP,0,,,E,
1149 | EZE00100082,18000818,TMAX,323,,,E,
1150 | EZE00100082,18000818,TMIN,185,,,E,
1151 | ITE00100554,18000819,TMAX,323,,,E,
1152 | ITE00100554,18000819,TMIN,238,,,E,
1153 | GM000010962,18000819,PRCP,0,,,E,
1154 | EZE00100082,18000819,TMAX,290,,,E,
1155 | EZE00100082,18000819,TMIN,195,,,E,
1156 | ITE00100554,18000820,TMAX,310,,,E,
1157 | ITE00100554,18000820,TMIN,235,,,E,
1158 | GM000010962,18000820,PRCP,0,,,E,
1159 | EZE00100082,18000820,TMAX,274,,,E,
1160 | EZE00100082,18000820,TMIN,202,,,E,
1161 | ITE00100554,18000821,TMAX,298,,,E,
1162 | ITE00100554,18000821,TMIN,231,,,E,
1163 | GM000010962,18000821,PRCP,36,,,E,
1164 | EZE00100082,18000821,TMAX,253,,,E,
1165 | EZE00100082,18000821,TMIN,195,,,E,
1166 | ITE00100554,18000822,TMAX,279,,,E,
1167 | ITE00100554,18000822,TMIN,209,,,E,
1168 | GM000010962,18000822,PRCP,195,,,E,
1169 | EZE00100082,18000822,TMAX,206,,,E,
1170 | EZE00100082,18000822,TMIN,158,,,E,
1171 | ITE00100554,18000823,TMAX,213,,,E,
1172 | ITE00100554,18000823,TMIN,204,,,E,
1173 | GM000010962,18000823,PRCP,0,,,E,
1174 | EZE00100082,18000823,TMAX,231,,,E,
1175 | EZE00100082,18000823,TMIN,119,,,E,
1176 | ITE00100554,18000824,TMAX,229,,,E,
1177 | ITE00100554,18000824,TMIN,148,,,E,
1178 | GM000010962,18000824,PRCP,33,,,E,
1179 | EZE00100082,18000824,TMAX,213,,,E,
1180 | EZE00100082,18000824,TMIN,154,,,E,
1181 | ITE00100554,18000825,TMAX,241,,,E,
1182 | ITE00100554,18000825,TMIN,171,,,E,
1183 | GM000010962,18000825,PRCP,0,,,E,
1184 | EZE00100082,18000825,TMAX,200,,,E,
1185 | EZE00100082,18000825,TMIN,133,,,E,
1186 | ITE00100554,18000826,TMAX,210,,,E,
1187 | ITE00100554,18000826,TMIN,159,,,E,
1188 | GM000010962,18000826,PRCP,51,,,E,
1189 | EZE00100082,18000826,TMAX,215,,,E,
1190 | EZE00100082,18000826,TMIN,151,,,E,
1191 | ITE00100554,18000827,TMAX,234,,,E,
1192 | ITE00100554,18000827,TMIN,146,,,E,
1193 | GM000010962,18000827,PRCP,268,,,E,
1194 | EZE00100082,18000827,TMAX,220,,,E,
1195 | EZE00100082,18000827,TMIN,148,,,E,
1196 | ITE00100554,18000828,TMAX,234,,,E,
1197 | ITE00100554,18000828,TMIN,154,,,E,
1198 | GM000010962,18000828,PRCP,0,,,E,
1199 | EZE00100082,18000828,TMAX,203,,,E,
1200 | EZE00100082,18000828,TMIN,158,,,E,
1201 | ITE00100554,18000829,TMAX,241,,,E,
1202 | ITE00100554,18000829,TMIN,179,,,E,
1203 | GM000010962,18000829,PRCP,0,,,E,
1204 | EZE00100082,18000829,TMAX,203,,,E,
1205 | EZE00100082,18000829,TMIN,149,,,E,
1206 | ITE00100554,18000830,TMAX,241,,,E,
1207 | ITE00100554,18000830,TMIN,163,,,E,
1208 | GM000010962,18000830,PRCP,40,,,E,
1209 | EZE00100082,18000830,TMAX,196,,,E,
1210 | EZE00100082,18000830,TMIN,154,,,E,
1211 | ITE00100554,18000831,TMAX,240,,,E,
1212 | ITE00100554,18000831,TMIN,165,,,E,
1213 | GM000010962,18000831,PRCP,50,,,E,
1214 | EZE00100082,18000831,TMAX,177,,,E,
1215 | EZE00100082,18000831,TMIN,147,,,E,
1216 | ITE00100554,18000901,TMAX,241,,,E,
1217 | ITE00100554,18000901,TMIN,184,,,E,
1218 | GM000010962,18000901,PRCP,31,,,E,
1219 | EZE00100082,18000901,TMAX,193,,,E,
1220 | EZE00100082,18000901,TMIN,148,,,E,
1221 | ITE00100554,18000902,TMAX,179,,,E,
1222 | ITE00100554,18000902,TMIN,179,,,E,
1223 | GM000010962,18000902,PRCP,0,,,E,
1224 | EZE00100082,18000902,TMAX,209,,,E,
1225 | EZE00100082,18000902,TMIN,152,,,E,
1226 | ITE00100554,18000903,TMAX,216,,,E,
1227 | ITE00100554,18000903,TMIN,166,,,E,
1228 | GM000010962,18000903,PRCP,2,,,E,
1229 | EZE00100082,18000903,TMAX,197,,,E,
1230 | EZE00100082,18000903,TMIN,157,,,E,
1231 | ITE00100554,18000904,TMAX,229,,,E,
1232 | ITE00100554,18000904,TMIN,166,,,E,
1233 | GM000010962,18000904,PRCP,2,,,E,
1234 | EZE00100082,18000904,TMAX,214,,,E,
1235 | EZE00100082,18000904,TMIN,141,,,E,
1236 | ITE00100554,18000905,TMAX,238,,,E,
1237 | ITE00100554,18000905,TMIN,191,,,E,
1238 | GM000010962,18000905,PRCP,0,,,E,
1239 | EZE00100082,18000905,TMAX,210,,,E,
1240 | EZE00100082,18000905,TMIN,154,,,E,
1241 | ITE00100554,18000906,TMAX,238,,,E,
1242 | ITE00100554,18000906,TMIN,179,,,E,
1243 | GM000010962,18000906,PRCP,20,,,E,
1244 | EZE00100082,18000906,TMAX,225,,,E,
1245 | EZE00100082,18000906,TMIN,173,,,E,
1246 | ITE00100554,18000907,TMAX,223,,,E,
1247 | ITE00100554,18000907,TMIN,178,,,E,
1248 | GM000010962,18000907,PRCP,0,,,E,
1249 | EZE00100082,18000907,TMAX,230,,,E,
1250 | EZE00100082,18000907,TMIN,146,,,E,
1251 | ITE00100554,18000908,TMAX,238,,,E,
1252 | ITE00100554,18000908,TMIN,175,,,E,
1253 | GM000010962,18000908,PRCP,56,,,E,
1254 | EZE00100082,18000908,TMAX,227,,,E,
1255 | EZE00100082,18000908,TMIN,184,,,E,
1256 | ITE00100554,18000909,TMAX,250,,,E,
1257 | ITE00100554,18000909,TMIN,188,,,E,
1258 | GM000010962,18000909,PRCP,11,,,E,
1259 | EZE00100082,18000909,TMAX,194,,,E,
1260 | EZE00100082,18000909,TMIN,163,,,E,
1261 | ITE00100554,18000910,TMAX,238,,,E,
1262 | ITE00100554,18000910,TMIN,188,,,E,
1263 | GM000010962,18000910,PRCP,0,,,E,
1264 | EZE00100082,18000910,TMAX,202,,,E,
1265 | EZE00100082,18000910,TMIN,152,,,E,
1266 | ITE00100554,18000911,TMAX,248,,,E,
1267 | ITE00100554,18000911,TMIN,163,,,E,
1268 | GM000010962,18000911,PRCP,110,,,E,
1269 | EZE00100082,18000911,TMAX,181,,,E,
1270 | EZE00100082,18000911,TMIN,157,,,E,
1271 | ITE00100554,18000912,TMAX,238,,,E,
1272 | ITE00100554,18000912,TMIN,163,,,E,
1273 | GM000010962,18000912,PRCP,1,,,E,
1274 | EZE00100082,18000912,TMAX,186,,,E,
1275 | EZE00100082,18000912,TMIN,141,,,E,
1276 | ITE00100554,18000913,TMAX,241,,,E,
1277 | ITE00100554,18000913,TMIN,154,,,E,
1278 | GM000010962,18000913,PRCP,0,,,E,
1279 | EZE00100082,18000913,TMAX,177,,,E,
1280 | EZE00100082,18000913,TMIN,116,,,E,
1281 | ITE00100554,18000914,TMAX,229,,,E,
1282 | ITE00100554,18000914,TMIN,166,,,E,
1283 | GM000010962,18000914,PRCP,0,,,E,
1284 | EZE00100082,18000914,TMAX,183,,,E,
1285 | EZE00100082,18000914,TMIN,104,,,E,
1286 | ITE00100554,18000915,TMAX,225,,,E,
1287 | ITE00100554,18000915,TMIN,159,,,E,
1288 | GM000010962,18000915,PRCP,0,,,E,
1289 | EZE00100082,18000915,TMAX,198,,,E,
1290 | EZE00100082,18000915,TMIN,115,,,E,
1291 | ITE00100554,18000916,TMAX,229,,,E,
1292 | ITE00100554,18000916,TMIN,154,,,E,
1293 | GM000010962,18000916,PRCP,0,,,E,
1294 | EZE00100082,18000916,TMAX,205,,,E,
1295 | EZE00100082,18000916,TMIN,111,,,E,
1296 | ITE00100554,18000917,TMAX,235,,,E,
1297 | ITE00100554,18000917,TMIN,163,,,E,
1298 | GM000010962,18000917,PRCP,0,,,E,
1299 | EZE00100082,18000917,TMAX,199,,,E,
1300 | EZE00100082,18000917,TMIN,110,,,E,
1301 | ITE00100554,18000918,TMAX,246,,,E,
1302 | ITE00100554,18000918,TMIN,175,,,E,
1303 | GM000010962,18000918,PRCP,4,,,E,
1304 | EZE00100082,18000918,TMAX,217,,,E,
1305 | EZE00100082,18000918,TMIN,118,,,E,
1306 | ITE00100554,18000919,TMAX,241,,,E,
1307 | ITE00100554,18000919,TMIN,184,,,E,
1308 | GM000010962,18000919,PRCP,0,,,E,
1309 | EZE00100082,18000919,TMAX,217,,,E,
1310 | EZE00100082,18000919,TMIN,165,,,E,
1311 | ITE00100554,18000920,TMAX,225,,,E,
1312 | ITE00100554,18000920,TMIN,191,,,E,
1313 | GM000010962,18000920,PRCP,2,,,E,
1314 | EZE00100082,18000920,TMAX,210,,,E,
1315 | EZE00100082,18000920,TMIN,142,,,E,
1316 | ITE00100554,18000921,TMAX,231,,,E,
1317 | ITE00100554,18000921,TMIN,191,,,E,
1318 | GM000010962,18000921,PRCP,85,,,E,
1319 | EZE00100082,18000921,TMAX,193,,,E,
1320 | EZE00100082,18000921,TMIN,155,,,E,
1321 | ITE00100554,18000922,TMAX,235,,,E,
1322 | ITE00100554,18000922,TMIN,185,,,E,
1323 | GM000010962,18000922,PRCP,33,,,E,
1324 | EZE00100082,18000922,TMAX,169,,,E,
1325 | EZE00100082,18000922,TMIN,136,,,E,
1326 | ITE00100554,18000923,TMAX,234,,,E,
1327 | ITE00100554,18000923,TMIN,163,,,E,
1328 | GM000010962,18000923,PRCP,14,,,E,
1329 | EZE00100082,18000923,TMAX,170,,,E,
1330 | EZE00100082,18000923,TMIN,131,,,E,
1331 | ITE00100554,18000924,TMAX,234,,,E,
1332 | ITE00100554,18000924,TMIN,169,,,E,
1333 | GM000010962,18000924,PRCP,49,,,E,
1334 | EZE00100082,18000924,TMAX,164,,,E,
1335 | EZE00100082,18000924,TMIN,132,,,E,
1336 | ITE00100554,18000925,TMAX,238,,,E,
1337 | ITE00100554,18000925,TMIN,171,,,E,
1338 | GM000010962,18000925,PRCP,30,,,E,
1339 | EZE00100082,18000925,TMAX,156,,,E,
1340 | EZE00100082,18000925,TMIN,125,,,E,
1341 | ITE00100554,18000926,TMAX,198,,,E,
1342 | ITE00100554,18000926,TMIN,181,,,E,
1343 | GM000010962,18000926,PRCP,10,,,E,
1344 | EZE00100082,18000926,TMAX,144,,,E,
1345 | EZE00100082,18000926,TMIN,115,,,E,
1346 | ITE00100554,18000927,TMAX,213,,,E,
1347 | ITE00100554,18000927,TMIN,129,,,E,
1348 | GM000010962,18000927,PRCP,11,,,E,
1349 | EZE00100082,18000927,TMAX,134,,,E,
1350 | EZE00100082,18000927,TMIN,116,,,E,
1351 | ITE00100554,18000928,TMAX,213,,,E,
1352 | ITE00100554,18000928,TMIN,181,,,E,
1353 | GM000010962,18000928,PRCP,14,,,E,
1354 | EZE00100082,18000928,TMAX,158,,,E,
1355 | EZE00100082,18000928,TMIN,114,,,E,
1356 | ITE00100554,18000929,TMAX,196,,,E,
1357 | ITE00100554,18000929,TMIN,119,,,E,
1358 | GM000010962,18000929,PRCP,13,,,E,
1359 | EZE00100082,18000929,TMAX,131,,,E,
1360 | EZE00100082,18000929,TMIN,91,,,E,
1361 | ITE00100554,18000930,TMAX,200,,,E,
1362 | ITE00100554,18000930,TMIN,100,,,E,
1363 | GM000010962,18000930,PRCP,0,,,E,
1364 | EZE00100082,18000930,TMAX,157,,,E,
1365 | EZE00100082,18000930,TMIN,85,,,E,
1366 | ITE00100554,18001001,TMAX,188,,,E,
1367 | ITE00100554,18001001,TMIN,129,,,E,
1368 | GM000010962,18001001,PRCP,45,,,E,
1369 | EZE00100082,18001001,TMAX,133,,,E,
1370 | EZE00100082,18001001,TMIN,110,,,E,
1371 | ITE00100554,18001002,TMAX,194,,,E,
1372 | ITE00100554,18001002,TMIN,144,,,E,
1373 | GM000010962,18001002,PRCP,127,,,E,
1374 | EZE00100082,18001002,TMAX,135,,,E,
1375 | EZE00100082,18001002,TMIN,98,,,E,
1376 | ITE00100554,18001003,TMAX,200,,,E,
1377 | ITE00100554,18001003,TMIN,144,,,E,
1378 | GM000010962,18001003,PRCP,149,,,E,
1379 | EZE00100082,18001003,TMAX,164,,,E,
1380 | EZE00100082,18001003,TMIN,94,,,E,
1381 | ITE00100554,18001004,TMAX,200,,,E,
1382 | ITE00100554,18001004,TMIN,163,,,E,
1383 | GM000010962,18001004,PRCP,48,,,E,
1384 | EZE00100082,18001004,TMAX,136,,,E,
1385 | EZE00100082,18001004,TMIN,109,,,E,
1386 | ITE00100554,18001005,TMAX,185,,,E,
1387 | ITE00100554,18001005,TMIN,141,,,E,
1388 | GM000010962,18001005,PRCP,0,,,E,
1389 | EZE00100082,18001005,TMAX,150,,,E,
1390 | EZE00100082,18001005,TMIN,95,,,E,
1391 | ITE00100554,18001006,TMAX,181,,,E,
1392 | ITE00100554,18001006,TMIN,150,,,E,
1393 | GM000010962,18001006,PRCP,0,,,E,
1394 | EZE00100082,18001006,TMAX,149,,,E,
1395 | EZE00100082,18001006,TMIN,76,,,E,
1396 | ITE00100554,18001007,TMAX,169,,,E,
1397 | ITE00100554,18001007,TMIN,154,,,E,
1398 | GM000010962,18001007,PRCP,0,,,E,
1399 | EZE00100082,18001007,TMAX,163,,,E,
1400 | EZE00100082,18001007,TMIN,98,,,E,
1401 | ITE00100554,18001008,TMAX,184,,,E,
1402 | ITE00100554,18001008,TMIN,165,,,E,
1403 | GM000010962,18001008,PRCP,0,,,E,
1404 | EZE00100082,18001008,TMAX,165,,,E,
1405 | EZE00100082,18001008,TMIN,104,,,E,
1406 | ITE00100554,18001009,TMAX,184,,,E,
1407 | ITE00100554,18001009,TMIN,166,,,E,
1408 | GM000010962,18001009,PRCP,49,,,E,
1409 | EZE00100082,18001009,TMAX,174,,,E,
1410 | EZE00100082,18001009,TMIN,120,,,E,
1411 | ITE00100554,18001010,TMAX,181,,,E,
1412 | ITE00100554,18001010,TMIN,150,,,E,
1413 | GM000010962,18001010,PRCP,32,,,E,
1414 | EZE00100082,18001010,TMAX,169,,,E,
1415 | EZE00100082,18001010,TMIN,125,,,E,
1416 | ITE00100554,18001011,TMAX,188,,,E,
1417 | ITE00100554,18001011,TMIN,150,,,E,
1418 | GM000010962,18001011,PRCP,32,,,E,
1419 | EZE00100082,18001011,TMAX,136,,,E,
1420 | EZE00100082,18001011,TMIN,97,,,E,
1421 | ITE00100554,18001012,TMAX,175,,,E,
1422 | ITE00100554,18001012,TMIN,123,,,E,
1423 | GM000010962,18001012,PRCP,0,,,E,
1424 | EZE00100082,18001012,TMAX,147,,,E,
1425 | EZE00100082,18001012,TMIN,99,,,E,
1426 | ITE00100554,18001013,TMAX,175,,,E,
1427 | ITE00100554,18001013,TMIN,113,,,E,
1428 | GM000010962,18001013,PRCP,11,,,E,
1429 | EZE00100082,18001013,TMAX,127,,,E,
1430 | EZE00100082,18001013,TMIN,98,,,E,
1431 | ITE00100554,18001014,TMAX,171,,,E,
1432 | ITE00100554,18001014,TMIN,100,,,E,
1433 | GM000010962,18001014,PRCP,0,,,E,
1434 | EZE00100082,18001014,TMAX,135,,,E,
1435 | EZE00100082,18001014,TMIN,93,,,E,
1436 | ITE00100554,18001015,TMAX,171,,,E,
1437 | ITE00100554,18001015,TMIN,96,,,E,
1438 | GM000010962,18001015,PRCP,0,,,E,
1439 | EZE00100082,18001015,TMAX,124,,,E,
1440 | EZE00100082,18001015,TMIN,97,,,E,
1441 | ITE00100554,18001016,TMAX,166,,,E,
1442 | ITE00100554,18001016,TMIN,109,,,E,
1443 | GM000010962,18001016,PRCP,33,,,E,
1444 | EZE00100082,18001016,TMAX,119,,,E,
1445 | EZE00100082,18001016,TMIN,72,,,E,
1446 | ITE00100554,18001017,TMAX,184,,,E,
1447 | ITE00100554,18001017,TMIN,116,,,E,
1448 | GM000010962,18001017,PRCP,15,,,E,
1449 | EZE00100082,18001017,TMAX,81,,,E,
1450 | EZE00100082,18001017,TMIN,48,,,E,
1451 | ITE00100554,18001018,TMAX,154,,,E,
1452 | ITE00100554,18001018,TMIN,104,,,E,
1453 | GM000010962,18001018,PRCP,11,,,E,
1454 | EZE00100082,18001018,TMAX,99,,,E,
1455 | EZE00100082,18001018,TMIN,22,,,E,
1456 | ITE00100554,18001019,TMAX,150,,,E,
1457 | ITE00100554,18001019,TMIN,75,,,E,
1458 | GM000010962,18001019,PRCP,0,,,E,
1459 | EZE00100082,18001019,TMAX,127,,,E,
1460 | EZE00100082,18001019,TMIN,85,,,E,
1461 | ITE00100554,18001020,TMAX,149,,,E,
1462 | ITE00100554,18001020,TMIN,69,,,E,
1463 | GM000010962,18001020,PRCP,0,,,E,
1464 | EZE00100082,18001020,TMAX,136,,,E,
1465 | EZE00100082,18001020,TMIN,75,,,E,
1466 | ITE00100554,18001021,TMAX,148,,,E,
1467 | ITE00100554,18001021,TMIN,71,,,E,
1468 | GM000010962,18001021,PRCP,0,,,E,
1469 | EZE00100082,18001021,TMAX,133,,,E,
1470 | EZE00100082,18001021,TMIN,60,,,E,
1471 | ITE00100554,18001022,TMAX,129,,,E,
1472 | ITE00100554,18001022,TMIN,110,,,E,
1473 | GM000010962,18001022,PRCP,12,,,E,
1474 | EZE00100082,18001022,TMAX,106,,,E,
1475 | EZE00100082,18001022,TMIN,52,,,E,
1476 | ITE00100554,18001023,TMAX,116,,,E,
1477 | ITE00100554,18001023,TMIN,113,,,E,
1478 | GM000010962,18001023,PRCP,11,,,E,
1479 | EZE00100082,18001023,TMAX,75,,,E,
1480 | EZE00100082,18001023,TMIN,44,,,E,
1481 | ITE00100554,18001024,TMAX,104,,,E,
1482 | ITE00100554,18001024,TMIN,44,,,E,
1483 | GM000010962,18001024,PRCP,0,,,E,
1484 | EZE00100082,18001024,TMAX,92,,,E,
1485 | EZE00100082,18001024,TMIN,33,,,E,
1486 | ITE00100554,18001025,TMAX,121,,,E,
1487 | ITE00100554,18001025,TMIN,31,,,E,
1488 | GM000010962,18001025,PRCP,0,,,E,
1489 | EZE00100082,18001025,TMAX,76,,,E,
1490 | EZE00100082,18001025,TMIN,-11,,,E,
1491 | ITE00100554,18001026,TMAX,129,,,E,
1492 | ITE00100554,18001026,TMIN,50,,,E,
1493 | GM000010962,18001026,PRCP,0,,,E,
1494 | EZE00100082,18001026,TMAX,90,,,E,
1495 | EZE00100082,18001026,TMIN,55,,,E,
1496 | ITE00100554,18001027,TMAX,134,,,E,
1497 | ITE00100554,18001027,TMIN,60,,,E,
1498 | GM000010962,18001027,PRCP,0,,,E,
1499 | EZE00100082,18001027,TMAX,102,,,E,
1500 | EZE00100082,18001027,TMIN,45,,,E,
1501 | ITE00100554,18001028,TMAX,148,,,E,
1502 | ITE00100554,18001028,TMIN,125,,,E,
1503 | GM000010962,18001028,PRCP,0,,,E,
1504 | EZE00100082,18001028,TMAX,99,,,E,
1505 | EZE00100082,18001028,TMIN,59,,,E,
1506 | ITE00100554,18001029,TMAX,150,,,E,
1507 | ITE00100554,18001029,TMIN,113,,,E,
1508 | GM000010962,18001029,PRCP,2,,,E,
1509 | EZE00100082,18001029,TMAX,97,,,E,
1510 | EZE00100082,18001029,TMIN,60,,,E,
1511 | ITE00100554,18001030,TMAX,150,,,E,
1512 | ITE00100554,18001030,TMIN,116,,,E,
1513 | GM000010962,18001030,PRCP,0,,,E,
1514 | EZE00100082,18001030,TMAX,123,,,E,
1515 | EZE00100082,18001030,TMIN,70,,,E,
1516 | ITE00100554,18001031,TMAX,125,,,E,
1517 | ITE00100554,18001031,TMIN,116,,,E,
1518 | GM000010962,18001031,PRCP,0,,,E,
1519 | EZE00100082,18001031,TMAX,90,,,E,
1520 | EZE00100082,18001031,TMIN,22,,,E,
1521 | ITE00100554,18001101,TMAX,150,,,E,
1522 | ITE00100554,18001101,TMIN,116,,,E,
1523 | GM000010962,18001101,PRCP,20,,,E,
1524 | EZE00100082,18001101,TMAX,88,,,E,
1525 | EZE00100082,18001101,TMIN,57,,,E,
1526 | ITE00100554,18001102,TMAX,141,,,E,
1527 | ITE00100554,18001102,TMIN,116,,,E,
1528 | GM000010962,18001102,PRCP,63,,,E,
1529 | EZE00100082,18001102,TMAX,93,,,E,
1530 | EZE00100082,18001102,TMIN,60,,,E,
1531 | ITE00100554,18001103,TMAX,135,,,E,
1532 | ITE00100554,18001103,TMIN,90,,,E,
1533 | GM000010962,18001103,PRCP,0,,,E,
1534 | EZE00100082,18001103,TMAX,114,,,E,
1535 | EZE00100082,18001103,TMIN,79,,,E,
1536 | ITE00100554,18001104,TMAX,113,,,E,
1537 | ITE00100554,18001104,TMIN,106,,,E,
1538 | GM000010962,18001104,PRCP,0,,,E,
1539 | EZE00100082,18001104,TMAX,116,,,E,
1540 | EZE00100082,18001104,TMIN,79,,,E,
1541 | ITE00100554,18001105,TMAX,109,,,E,
1542 | ITE00100554,18001105,TMIN,100,,,E,
1543 | GM000010962,18001105,PRCP,54,,,E,
1544 | EZE00100082,18001105,TMAX,85,,,E,
1545 | EZE00100082,18001105,TMIN,61,,,E,
1546 | ITE00100554,18001106,TMAX,113,,,E,
1547 | ITE00100554,18001106,TMIN,48,,,E,
1548 | GM000010962,18001106,PRCP,59,,,E,
1549 | EZE00100082,18001106,TMAX,84,,,E,
1550 | EZE00100082,18001106,TMIN,51,,,E,
1551 | ITE00100554,18001107,TMAX,123,,,E,
1552 | ITE00100554,18001107,TMIN,50,,,E,
1553 | GM000010962,18001107,PRCP,25,,,E,
1554 | EZE00100082,18001107,TMAX,86,,,E,
1555 | EZE00100082,18001107,TMIN,45,,,E,
1556 | ITE00100554,18001108,TMAX,110,,,E,
1557 | ITE00100554,18001108,TMIN,98,,,E,
1558 | GM000010962,18001108,PRCP,0,,,E,
1559 | EZE00100082,18001108,TMAX,122,,,E,
1560 | EZE00100082,18001108,TMIN,74,,,E,
1561 | ITE00100554,18001109,TMAX,113,,,E,
1562 | ITE00100554,18001109,TMIN,109,,,E,
1563 | GM000010962,18001109,PRCP,4,,,E,
1564 | EZE00100082,18001109,TMAX,173,,,E,
1565 | EZE00100082,18001109,TMIN,122,,,E,
1566 | ITE00100554,18001110,TMAX,146,,,E,
1567 | ITE00100554,18001110,TMIN,104,,,E,
1568 | GM000010962,18001110,PRCP,0,,,E,
1569 | EZE00100082,18001110,TMAX,147,,,E,
1570 | EZE00100082,18001110,TMIN,64,,,E,
1571 | ITE00100554,18001111,TMAX,146,,,E,
1572 | ITE00100554,18001111,TMIN,116,,,E,
1573 | GM000010962,18001111,PRCP,0,,,E,
1574 | EZE00100082,18001111,TMAX,97,,,E,
1575 | EZE00100082,18001111,TMIN,43,,,E,
1576 | ITE00100554,18001112,TMAX,134,,,E,
1577 | ITE00100554,18001112,TMIN,121,,,E,
1578 | GM000010962,18001112,PRCP,0,,,E,
1579 | EZE00100082,18001112,TMAX,103,,,E,
1580 | EZE00100082,18001112,TMIN,45,,,E,
1581 | ITE00100554,18001113,TMAX,113,,,E,
1582 | ITE00100554,18001113,TMIN,98,,,E,
1583 | GM000010962,18001113,PRCP,42,,,E,
1584 | EZE00100082,18001113,TMAX,80,,,E,
1585 | EZE00100082,18001113,TMIN,50,,,E,
1586 | ITE00100554,18001114,TMAX,131,,,E,
1587 | ITE00100554,18001114,TMIN,88,,,E,
1588 | GM000010962,18001114,PRCP,39,,,E,
1589 | EZE00100082,18001114,TMAX,81,,,E,
1590 | EZE00100082,18001114,TMIN,27,,,E,
1591 | ITE00100554,18001115,TMAX,119,,,E,
1592 | ITE00100554,18001115,TMIN,66,,,E,
1593 | GM000010962,18001115,PRCP,0,,,E,
1594 | EZE00100082,18001115,TMAX,44,,,E,
1595 | EZE00100082,18001115,TMIN,1,,,E,
1596 | ITE00100554,18001116,TMAX,94,,,E,
1597 | ITE00100554,18001116,TMIN,94,,,E,
1598 | GM000010962,18001116,PRCP,0,,,E,
1599 | EZE00100082,18001116,TMAX,63,,,E,
1600 | EZE00100082,18001116,TMIN,30,,,E,
1601 | ITE00100554,18001117,TMAX,94,,,E,
1602 | ITE00100554,18001117,TMIN,79,,,E,
1603 | GM000010962,18001117,PRCP,47,,,E,
1604 | EZE00100082,18001117,TMAX,70,,,E,
1605 | EZE00100082,18001117,TMIN,44,,,E,
1606 | ITE00100554,18001118,TMAX,98,,,E,
1607 | ITE00100554,18001118,TMIN,54,,,E,
1608 | GM000010962,18001118,PRCP,13,,,E,
1609 | EZE00100082,18001118,TMAX,70,,,E,
1610 | EZE00100082,18001118,TMIN,50,,,E,
1611 | ITE00100554,18001119,TMAX,109,,,E,
1612 | ITE00100554,18001119,TMIN,81,,,E,
1613 | GM000010962,18001119,PRCP,114,,,E,
1614 | EZE00100082,18001119,TMAX,68,,,E,
1615 | EZE00100082,18001119,TMIN,55,,,E,
1616 | ITE00100554,18001120,TMAX,116,,,E,
1617 | ITE00100554,18001120,TMIN,54,,,E,
1618 | GM000010962,18001120,PRCP,62,,,E,
1619 | EZE00100082,18001120,TMAX,57,,,E,
1620 | EZE00100082,18001120,TMIN,15,,,E,
1621 | ITE00100554,18001121,TMAX,91,,,E,
1622 | ITE00100554,18001121,TMIN,46,,,E,
1623 | GM000010962,18001121,PRCP,7,,,E,
1624 | EZE00100082,18001121,TMAX,29,,,E,
1625 | EZE00100082,18001121,TMIN,2,,,E,
1626 | ITE00100554,18001122,TMAX,60,,,E,
1627 | ITE00100554,18001122,TMIN,54,,,E,
1628 | GM000010962,18001122,PRCP,0,,,E,
1629 | EZE00100082,18001122,TMAX,34,,,E,
1630 | EZE00100082,18001122,TMIN,0,,,E,
1631 | ITE00100554,18001123,TMAX,69,,,E,
1632 | ITE00100554,18001123,TMIN,21,,,E,
1633 | GM000010962,18001123,PRCP,0,,,E,
1634 | EZE00100082,18001123,TMAX,58,,,E,
1635 | EZE00100082,18001123,TMIN,30,,,E,
1636 | ITE00100554,18001124,TMAX,63,,,E,
1637 | ITE00100554,18001124,TMIN,19,,,E,
1638 | GM000010962,18001124,PRCP,0,,,E,
1639 | EZE00100082,18001124,TMAX,69,,,E,
1640 | EZE00100082,18001124,TMIN,14,,,E,
1641 | ITE00100554,18001125,TMAX,63,,,E,
1642 | ITE00100554,18001125,TMIN,40,,,E,
1643 | GM000010962,18001125,PRCP,0,,,E,
1644 | EZE00100082,18001125,TMAX,43,,,E,
1645 | EZE00100082,18001125,TMIN,-5,,,E,
1646 | ITE00100554,18001126,TMAX,59,,,E,
1647 | ITE00100554,18001126,TMIN,54,,,E,
1648 | GM000010962,18001126,PRCP,0,,,E,
1649 | EZE00100082,18001126,TMAX,45,,,E,
1650 | EZE00100082,18001126,TMIN,-6,,,E,
1651 | ITE00100554,18001127,TMAX,48,,,E,
1652 | ITE00100554,18001127,TMIN,41,,,E,
1653 | GM000010962,18001127,PRCP,86,,,E,
1654 | EZE00100082,18001127,TMAX,56,,,E,
1655 | EZE00100082,18001127,TMIN,38,,,E,
1656 | ITE00100554,18001128,TMAX,63,,,E,
1657 | ITE00100554,18001128,TMIN,48,,,E,
1658 | GM000010962,18001128,PRCP,56,,,E,
1659 | EZE00100082,18001128,TMAX,38,,,E,
1660 | EZE00100082,18001128,TMIN,17,,,E,
1661 | ITE00100554,18001129,TMAX,66,,,E,
1662 | ITE00100554,18001129,TMIN,59,,,E,
1663 | GM000010962,18001129,PRCP,13,,,E,
1664 | EZE00100082,18001129,TMAX,42,,,E,
1665 | EZE00100082,18001129,TMIN,17,,,E,
1666 | ITE00100554,18001130,TMAX,66,,,E,
1667 | ITE00100554,18001130,TMIN,25,,,E,
1668 | GM000010962,18001130,PRCP,0,,,E,
1669 | EZE00100082,18001130,TMAX,22,,,E,
1670 | EZE00100082,18001130,TMIN,0,,,E,
1671 | ITE00100554,18001201,TMAX,29,,,E,
1672 | ITE00100554,18001201,TMIN,9,,,E,
1673 | GM000010962,18001201,PRCP,7,,,E,
1674 | EZE00100082,18001201,TMAX,34,,,E,
1675 | EZE00100082,18001201,TMIN,-2,,,E,
1676 | ITE00100554,18001202,TMAX,10,,,E,
1677 | ITE00100554,18001202,TMIN,-23,,,E,
1678 | GM000010962,18001202,PRCP,0,,,E,
1679 | EZE00100082,18001202,TMAX,39,,,E,
1680 | EZE00100082,18001202,TMIN,-5,,,E,
1681 | ITE00100554,18001203,TMAX,16,,,E,
1682 | ITE00100554,18001203,TMIN,-4,,,E,
1683 | GM000010962,18001203,PRCP,14,,,E,
1684 | EZE00100082,18001203,TMAX,49,,,E,
1685 | EZE00100082,18001203,TMIN,11,,,E,
1686 | ITE00100554,18001204,TMAX,13,,,E,
1687 | ITE00100554,18001204,TMIN,4,,,E,
1688 | GM000010962,18001204,PRCP,0,,,E,
1689 | EZE00100082,18001204,TMAX,34,,,E,
1690 | EZE00100082,18001204,TMIN,-5,,,E,
1691 | ITE00100554,18001205,TMAX,54,,,E,
1692 | ITE00100554,18001205,TMIN,19,,,E,
1693 | GM000010962,18001205,PRCP,0,,,E,
1694 | EZE00100082,18001205,TMAX,23,,,E,
1695 | EZE00100082,18001205,TMIN,4,,,E,
1696 | ITE00100554,18001206,TMAX,29,,,E,
1697 | ITE00100554,18001206,TMIN,13,,,E,
1698 | GM000010962,18001206,PRCP,0,,,E,
1699 | EZE00100082,18001206,TMAX,63,,,E,
1700 | EZE00100082,18001206,TMIN,19,,,E,
1701 | ITE00100554,18001207,TMAX,13,,,E,
1702 | ITE00100554,18001207,TMIN,3,,,E,
1703 | GM000010962,18001207,PRCP,0,,,E,
1704 | EZE00100082,18001207,TMAX,38,,,E,
1705 | EZE00100082,18001207,TMIN,0,,,E,
1706 | ITE00100554,18001208,TMAX,0,,,E,
1707 | ITE00100554,18001208,TMIN,-4,,,E,
1708 | GM000010962,18001208,PRCP,0,,,E,
1709 | EZE00100082,18001208,TMAX,24,,,E,
1710 | EZE00100082,18001208,TMIN,-4,,,E,
1711 | ITE00100554,18001209,TMAX,10,,,E,
1712 | ITE00100554,18001209,TMIN,-10,,,E,
1713 | GM000010962,18001209,PRCP,0,,,E,
1714 | EZE00100082,18001209,TMAX,24,,,E,
1715 | EZE00100082,18001209,TMIN,-17,,,E,
1716 | ITE00100554,18001210,TMAX,21,,I,E,
1717 | ITE00100554,18001210,TMIN,10,,,E,
1718 | GM000010962,18001210,PRCP,0,,,E,
1719 | EZE00100082,18001210,TMAX,27,,,E,
1720 | EZE00100082,18001210,TMIN,-9,,,E,
1721 | ITE00100554,18001211,TMAX,41,,,E,
1722 | ITE00100554,18001211,TMIN,35,,I,E,
1723 | GM000010962,18001211,PRCP,0,,,E,
1724 | EZE00100082,18001211,TMAX,47,,,E,
1725 | EZE00100082,18001211,TMIN,23,,,E,
1726 | ITE00100554,18001212,TMAX,46,,,E,
1727 | ITE00100554,18001212,TMIN,29,,,E,
1728 | GM000010962,18001212,PRCP,0,,,E,
1729 | EZE00100082,18001212,TMAX,44,,,E,
1730 | EZE00100082,18001212,TMIN,35,,,E,
1731 | ITE00100554,18001213,TMAX,71,,,E,
1732 | ITE00100554,18001213,TMIN,46,,,E,
1733 | GM000010962,18001213,PRCP,0,,,E,
1734 | EZE00100082,18001213,TMAX,45,,,E,
1735 | EZE00100082,18001213,TMIN,35,,,E,
1736 | ITE00100554,18001214,TMAX,85,,,E,
1737 | ITE00100554,18001214,TMIN,66,,,E,
1738 | GM000010962,18001214,PRCP,0,,,E,
1739 | EZE00100082,18001214,TMAX,38,,,E,
1740 | EZE00100082,18001214,TMIN,27,,,E,
1741 | ITE00100554,18001215,TMAX,91,,,E,
1742 | ITE00100554,18001215,TMIN,73,,,E,
1743 | GM000010962,18001215,PRCP,0,,,E,
1744 | EZE00100082,18001215,TMAX,27,,,E,
1745 | EZE00100082,18001215,TMIN,23,,,E,
1746 | ITE00100554,18001216,TMAX,66,,,E,
1747 | ITE00100554,18001216,TMIN,60,,,E,
1748 | GM000010962,18001216,PRCP,0,,,E,
1749 | EZE00100082,18001216,TMAX,23,,,E,
1750 | EZE00100082,18001216,TMIN,-3,,,E,
1751 | ITE00100554,18001217,TMAX,50,,,E,
1752 | ITE00100554,18001217,TMIN,50,,,E,
1753 | GM000010962,18001217,PRCP,0,,,E,
1754 | EZE00100082,18001217,TMAX,-1,,,E,
1755 | EZE00100082,18001217,TMIN,-14,,,E,
1756 | ITE00100554,18001218,TMAX,54,,,E,
1757 | ITE00100554,18001218,TMIN,48,,I,E,
1758 | GM000010962,18001218,PRCP,0,,,E,
1759 | EZE00100082,18001218,TMAX,-8,,,E,
1760 | EZE00100082,18001218,TMIN,-35,,,E,
1761 | ITE00100554,18001219,TMAX,29,,I,E,
1762 | ITE00100554,18001219,TMIN,29,,I,E,
1763 | GM000010962,18001219,PRCP,0,,,E,
1764 | EZE00100082,18001219,TMAX,-14,,,E,
1765 | EZE00100082,18001219,TMIN,-56,,,E,
1766 | ITE00100554,18001220,TMAX,13,,I,E,
1767 | ITE00100554,18001220,TMIN,10,,,E,
1768 | GM000010962,18001220,PRCP,0,,,E,
1769 | EZE00100082,18001220,TMAX,-14,,,E,
1770 | EZE00100082,18001220,TMIN,-64,,,E,
1771 | ITE00100554,18001221,TMAX,10,,,E,
1772 | ITE00100554,18001221,TMIN,-13,,,E,
1773 | GM000010962,18001221,PRCP,0,,,E,
1774 | EZE00100082,18001221,TMAX,4,,,E,
1775 | EZE00100082,18001221,TMIN,-83,,,E,
1776 | ITE00100554,18001222,TMAX,16,,,E,
1777 | ITE00100554,18001222,TMIN,-13,,,E,
1778 | GM000010962,18001222,PRCP,13,,,E,
1779 | EZE00100082,18001222,TMAX,54,,,E,
1780 | EZE00100082,18001222,TMIN,4,,,E,
1781 | ITE00100554,18001223,TMAX,23,,,E,
1782 | ITE00100554,18001223,TMIN,-16,,,E,
1783 | GM000010962,18001223,PRCP,0,,,E,
1784 | EZE00100082,18001223,TMAX,52,,,E,
1785 | EZE00100082,18001223,TMIN,30,,,E,
1786 | ITE00100554,18001224,TMAX,16,,,E,
1787 | ITE00100554,18001224,TMIN,4,,,E,
1788 | GM000010962,18001224,PRCP,0,,,E,
1789 | EZE00100082,18001224,TMAX,30,,,E,
1790 | EZE00100082,18001224,TMIN,6,,,E,
1791 | ITE00100554,18001225,TMAX,25,,,E,
1792 | ITE00100554,18001225,TMIN,13,,,E,
1793 | GM000010962,18001225,PRCP,0,,,E,
1794 | EZE00100082,18001225,TMAX,21,,,E,
1795 | EZE00100082,18001225,TMIN,11,,,E,
1796 | ITE00100554,18001226,TMAX,38,,,E,
1797 | ITE00100554,18001226,TMIN,25,,,E,
1798 | GM000010962,18001226,PRCP,0,,,E,
1799 | EZE00100082,18001226,TMAX,36,,,E,
1800 | EZE00100082,18001226,TMIN,8,,,E,
1801 | ITE00100554,18001227,TMAX,10,,I,E,
1802 | ITE00100554,18001227,TMIN,9,,,E,
1803 | GM000010962,18001227,PRCP,0,,,E,
1804 | EZE00100082,18001227,TMAX,47,,,E,
1805 | EZE00100082,18001227,TMIN,20,,,E,
1806 | ITE00100554,18001228,TMAX,35,,,E,
1807 | ITE00100554,18001228,TMIN,25,,,E,
1808 | GM000010962,18001228,PRCP,7,,,E,
1809 | EZE00100082,18001228,TMAX,43,,,E,
1810 | EZE00100082,18001228,TMIN,7,,,E,
1811 | ITE00100554,18001229,TMAX,50,,,E,
1812 | ITE00100554,18001229,TMIN,16,,,E,
1813 | GM000010962,18001229,PRCP,9,,,E,
1814 | EZE00100082,18001229,TMAX,45,,,E,
1815 | EZE00100082,18001229,TMIN,-3,,,E,
1816 | ITE00100554,18001230,TMAX,50,,,E,
1817 | ITE00100554,18001230,TMIN,31,,,E,
1818 | GM000010962,18001230,PRCP,13,,,E,
1819 | EZE00100082,18001230,TMAX,96,,,E,
1820 | EZE00100082,18001230,TMIN,14,,,E,
1821 | ITE00100554,18001231,TMAX,50,,,E,
1822 | ITE00100554,18001231,TMIN,25,,,E,
1823 | GM000010962,18001231,PRCP,16,,,E,
1824 | EZE00100082,18001231,TMAX,14,,,E,
1825 | EZE00100082,18001231,TMIN,-4,,,E,
1826 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2017 Packt
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/Marvel-names.txt:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PacktPublishing/Frank-Kanes-Taming-Big-Data-with-Apache-Spark-and-Python/67da5261c71f924938da9e51273ac390c759f7ca/Marvel-names.txt


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | 
 2 | 
 3 | 
 4 | # Frank Kane's Taming Big Data with Apache Spark and Python
 5 | This is the code repository for [Frank Kane's Taming Big Data with Apache Spark and Python](https://www.packtpub.com/big-data-and-business-intelligence/frank-kanes-taming-big-data-apache-spark-and-python?utm_source=github&utm_medium=repository&utm_campaign=9781787287945), published by [Packt](https://www.packtpub.com/?utm_source=github). It contains all the supporting project files necessary to work through the book from start to finish.
 6 | ## About the Book
 7 | Frank Kane’s Taming Big Data with Apache Spark and Python is your companion to learning Apache Spark in a hands-on manner. Frank will start you off by teaching you how to set up Spark on a single system or on a cluster, and you’ll soon move on to analyzing large data sets using Spark RDD, and developing and running effective Spark jobs quickly using Python.
 8 | 
 9 | Apache Spark has emerged as the next big thing in the Big Data domain – quickly rising from an ascending technology to an established superstar in just a matter of years. Spark allows you to quickly extract actionable insights from large amounts of data, on a real-time basis, making it an essential tool in many modern businesses.
10 | 
11 | Frank has packed this book with over 15 interactive, fun-filled examples relevant to the real world, and he will empower you to understand the Spark ecosystem and implement production-grade real-time Spark projects with ease.
12 | ##Instructions and Navigation
13 | All of the code is organized into folders. Each folder starts with a number followed by the application name. For example, Chapter02.
14 | 
15 | 
16 | 
17 | The code will look like the following:
18 | ```
19 | from pyspark import SparkConf, SparkContext 
20 | 
21 | import collections 
22 | 
23 | conf = SparkConf().setMaster("local").setAppName("RatingsHistogram") 
24 | sc = SparkContext(conf = conf)
25 | 
26 | lines = sc.textFile("file:///SparkCourse/ml-100k/u.data") 
27 | ratings = lines.map(lambda x: x.split()[2]) 
28 | result = ratings.countByValue() 
29 | 
30 | sortedResults = collections.OrderedDict(sorted(result.items())) 
31 | for key, value in sortedResults.items(): 
32 |     print("%s %i" % (key, value)) 
33 | ```
34 | 
35 | For this book you’ll need a Python development environment (Python 3.5 or newer), a Canopy installer, Java Development Kit, and of course Spark itself (Spark 2.0 and beyond).
36 | 
37 | 
38 | We'll show you how to install this software in first chapter of the book.
39 | 
40 | 
41 | This book is based on the Windows operating system, so installations are provided according to it. If you have Mac or Linux, you can follow this URL http://media.sundog-soft.com/spark-python-install.pdf, which contains written instructions on getting everything set up on Mac OS and on Linux.
42 | 
43 | ## Related Products
44 | * [Taming Big Data with Spark Streaming and Scala – Hands On! [Video]](https://www.packtpub.com/big-data-and-business-intelligence/taming-big-data-spark-streaming-and-scala-–-hands-video?utm_source=github&utm_medium=repository&utm_campaign=9781787123915)
45 | 
46 | * [Taming Big Data with Apache Spark and Python - Hands On! [Video]](https://www.packtpub.com/big-data-and-business-intelligence/taming-big-data-apache-spark-and-python-hands-video?utm_source=github&utm_medium=repository&utm_campaign=9781787129931)
47 | 
48 | * [Taming Big Data with MapReduce and Hadoop - Hands On! [Video]](https://www.packtpub.com/big-data-and-business-intelligence/taming-big-data-mapreduce-and-hadoop-hands-video?utm_source=github&utm_medium=repository&utm_campaign=9781787125568)
49 | 
50 | ### Download a free PDF
51 | 
52 |  <i>If you have already purchased a print or Kindle version of this book, you can get a DRM-free PDF version at no cost.<br>Simply click on the link to claim your free PDF.</i>
53 | <p align="center"> <a href="https://packt.link/free-ebook/9781787287945">https://packt.link/free-ebook/9781787287945 </a> </p>


--------------------------------------------------------------------------------
/book.txt:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PacktPublishing/Frank-Kanes-Taming-Big-Data-with-Apache-Spark-and-Python/67da5261c71f924938da9e51273ac390c759f7ca/book.txt


--------------------------------------------------------------------------------
/degrees-of-separation.py:
--------------------------------------------------------------------------------
  1 | #Boilerplate stuff:
  2 | from pyspark import SparkConf, SparkContext
  3 | 
  4 | conf = SparkConf().setMaster("local").setAppName("DegreesOfSeparation")
  5 | sc = SparkContext(conf = conf)
  6 | 
  7 | # The characters we wish to find the degree of separation between:
  8 | startCharacterID = 5306 #SpiderMan
  9 | targetCharacterID = 14  #ADAM 3,031 (who?)
 10 | 
 11 | # Our accumulator, used to signal when we find the target character during
 12 | # our BFS traversal.
 13 | hitCounter = sc.accumulator(0)
 14 | 
 15 | def convertToBFS(line):
 16 |     fields = line.split()
 17 |     heroID = int(fields[0])
 18 |     connections = []
 19 |     for connection in fields[1:]:
 20 |         connections.append(int(connection))
 21 | 
 22 |     color = 'WHITE'
 23 |     distance = 9999
 24 | 
 25 |     if (heroID == startCharacterID):
 26 |         color = 'GRAY'
 27 |         distance = 0
 28 | 
 29 |     return (heroID, (connections, distance, color))
 30 | 
 31 | 
 32 | def createStartingRdd():
 33 |     inputFile = sc.textFile("file:///sparkcourse/marvel-graph.txt")
 34 |     return inputFile.map(convertToBFS)
 35 | 
 36 | def bfsMap(node):
 37 |     characterID = node[0]
 38 |     data = node[1]
 39 |     connections = data[0]
 40 |     distance = data[1]
 41 |     color = data[2]
 42 | 
 43 |     results = []
 44 | 
 45 |     #If this node needs to be expanded...
 46 |     if (color == 'GRAY'):
 47 |         for connection in connections:
 48 |             newCharacterID = connection
 49 |             newDistance = distance + 1
 50 |             newColor = 'GRAY'
 51 |             if (targetCharacterID == connection):
 52 |                 hitCounter.add(1)
 53 | 
 54 |             newEntry = (newCharacterID, ([], newDistance, newColor))
 55 |             results.append(newEntry)
 56 | 
 57 |         #We've processed this node, so color it black
 58 |         color = 'BLACK'
 59 | 
 60 |     #Emit the input node so we don't lose it.
 61 |     results.append( (characterID, (connections, distance, color)) )
 62 |     return results
 63 | 
 64 | def bfsReduce(data1, data2):
 65 |     edges1 = data1[0]
 66 |     edges2 = data2[0]
 67 |     distance1 = data1[1]
 68 |     distance2 = data2[1]
 69 |     color1 = data1[2]
 70 |     color2 = data2[2]
 71 | 
 72 |     distance = 9999
 73 |     color = 'WHITE'
 74 |     edges = []
 75 | 
 76 |     # See if one is the original node with its connections.
 77 |     # If so preserve them.
 78 |     if (len(edges1) > 0):
 79 |         edges.extend(edges1)
 80 |     if (len(edges2) > 0):
 81 |         edges.extend(edges2)
 82 | 
 83 |     # Preserve minimum distance
 84 |     if (distance1 < distance):
 85 |         distance = distance1
 86 | 
 87 |     if (distance2 < distance):
 88 |         distance = distance2
 89 | 
 90 |     # Preserve darkest color
 91 |     if (color1 == 'WHITE' and (color2 == 'GRAY' or color2 == 'BLACK')):
 92 |         color = color2
 93 | 
 94 |     if (color1 == 'GRAY' and color2 == 'BLACK'):
 95 |         color = color2
 96 | 
 97 |     if (color2 == 'WHITE' and (color1 == 'GRAY' or color1 == 'BLACK')):
 98 |         color = color1
 99 | 
100 |     if (color2 == 'GRAY' and color1 == 'BLACK'):
101 |         color = color1
102 | 
103 |     return (edges, distance, color)
104 | 
105 | 
106 | #Main program here:
107 | iterationRdd = createStartingRdd()
108 | 
109 | for iteration in range(0, 10):
110 |     print("Running BFS iteration# " + str(iteration+1))
111 | 
112 |     # Create new vertices as needed to darken or reduce distances in the
113 |     # reduce stage. If we encounter the node we're looking for as a GRAY
114 |     # node, increment our accumulator to signal that we're done.
115 |     mapped = iterationRdd.flatMap(bfsMap)
116 | 
117 |     # Note that mapped.count() action here forces the RDD to be evaluated, and
118 |     # that's the only reason our accumulator is actually updated.
119 |     print("Processing " + str(mapped.count()) + " values.")
120 | 
121 |     if (hitCounter.value > 0):
122 |         print("Hit the target character! From " + str(hitCounter.value) \
123 |             + " different direction(s).")
124 |         break
125 | 
126 |     # Reducer combines data for each character ID, preserving the darkest
127 |     # color and shortest path.
128 |     iterationRdd = mapped.reduceByKey(bfsReduce)
129 | 


--------------------------------------------------------------------------------
/fakefriends.csv:
--------------------------------------------------------------------------------
  1 | 0,Will,33,385
  2 | 1,Jean-Luc,26,2
  3 | 2,Hugh,55,221
  4 | 3,Deanna,40,465
  5 | 4,Quark,68,21
  6 | 5,Weyoun,59,318
  7 | 6,Gowron,37,220
  8 | 7,Will,54,307
  9 | 8,Jadzia,38,380
 10 | 9,Hugh,27,181
 11 | 10,Odo,53,191
 12 | 11,Ben,57,372
 13 | 12,Keiko,54,253
 14 | 13,Jean-Luc,56,444
 15 | 14,Hugh,43,49
 16 | 15,Rom,36,49
 17 | 16,Weyoun,22,323
 18 | 17,Odo,35,13
 19 | 18,Jean-Luc,45,455
 20 | 19,Geordi,60,246
 21 | 20,Odo,67,220
 22 | 21,Miles,19,268
 23 | 22,Quark,30,72
 24 | 23,Keiko,51,271
 25 | 24,Julian,25,1
 26 | 25,Ben,21,445
 27 | 26,Julian,22,100
 28 | 27,Leeta,42,363
 29 | 28,Martok,49,476
 30 | 29,Nog,48,364
 31 | 30,Keiko,50,175
 32 | 31,Miles,39,161
 33 | 32,Nog,26,281
 34 | 33,Dukat,53,197
 35 | 34,Jean-Luc,43,249
 36 | 35,Beverly,27,305
 37 | 36,Kasidy,32,81
 38 | 37,Geordi,58,21
 39 | 38,Deanna,64,65
 40 | 39,Morn,31,192
 41 | 40,Odo,52,413
 42 | 41,Hugh,67,167
 43 | 42,Brunt,54,75
 44 | 43,Guinan,58,345
 45 | 44,Nerys,35,244
 46 | 45,Dukat,52,77
 47 | 46,Morn,25,96
 48 | 47,Brunt,24,49
 49 | 48,Nog,20,1
 50 | 49,Ezri,40,254
 51 | 50,Quark,51,283
 52 | 51,Lwaxana,36,212
 53 | 52,Beverly,19,269
 54 | 53,Geordi,62,31
 55 | 54,Brunt,19,5
 56 | 55,Keiko,41,278
 57 | 56,Gowron,44,194
 58 | 57,Odo,57,294
 59 | 58,Hugh,59,158
 60 | 59,Morn,59,284
 61 | 60,Geordi,20,100
 62 | 61,Kasidy,62,442
 63 | 62,Keiko,69,9
 64 | 63,Jean-Luc,58,54
 65 | 64,Elim,31,15
 66 | 65,Guinan,52,169
 67 | 66,Geordi,21,477
 68 | 67,Jadzia,48,135
 69 | 68,Guinan,33,74
 70 | 69,Jean-Luc,30,204
 71 | 70,Brunt,52,393
 72 | 71,Geordi,45,184
 73 | 72,Kasidy,22,179
 74 | 73,Brunt,20,384
 75 | 74,Leeta,65,208
 76 | 75,Morn,40,459
 77 | 76,Will,62,201
 78 | 77,Weyoun,40,407
 79 | 78,Data,61,337
 80 | 79,Leeta,58,348
 81 | 80,Dukat,67,445
 82 | 81,Jadzia,54,440
 83 | 82,Hugh,57,465
 84 | 83,Geordi,32,308
 85 | 84,Ben,28,311
 86 | 85,Quark,66,383
 87 | 86,Hugh,55,257
 88 | 87,Ezri,31,481
 89 | 88,Ben,66,188
 90 | 89,Worf,24,492
 91 | 90,Kasidy,33,471
 92 | 91,Rom,46,88
 93 | 92,Gowron,54,7
 94 | 93,Elim,46,63
 95 | 94,Morn,62,133
 96 | 95,Odo,29,173
 97 | 96,Ezri,25,233
 98 | 97,Nerys,69,361
 99 | 98,Will,44,178
100 | 99,Keiko,69,491
101 | 100,Jean-Luc,61,460
102 | 101,Morn,67,123
103 | 102,Dukat,40,18
104 | 103,Ezri,61,2
105 | 104,Dukat,32,142
106 | 105,Morn,50,417
107 | 106,Beverly,18,499
108 | 107,Will,64,419
109 | 108,Leeta,25,274
110 | 109,Quark,53,417
111 | 110,Nog,64,137
112 | 111,Nerys,37,46
113 | 112,Morn,25,13
114 | 113,Quark,41,244
115 | 114,Worf,33,275
116 | 115,Dukat,18,397
117 | 116,Ben,69,75
118 | 117,Rom,52,487
119 | 118,Ben,28,304
120 | 119,Worf,29,344
121 | 120,Jean-Luc,68,264
122 | 121,Deanna,35,355
123 | 122,Data,45,400
124 | 123,Jadzia,45,439
125 | 124,Data,47,429
126 | 125,Rom,66,284
127 | 126,Brunt,26,84
128 | 127,Miles,40,284
129 | 128,Julian,34,221
130 | 129,Kasidy,45,252
131 | 130,Gowron,67,350
132 | 131,Hugh,65,309
133 | 132,Odo,46,462
134 | 133,Quark,19,265
135 | 134,Ben,45,340
136 | 135,Rom,42,427
137 | 136,Will,19,335
138 | 137,Martok,28,32
139 | 138,Dukat,32,384
140 | 139,Nog,36,193
141 | 140,Elim,64,234
142 | 141,Miles,36,424
143 | 142,Guinan,59,335
144 | 143,Data,60,124
145 | 144,Miles,22,93
146 | 145,Leeta,45,470
147 | 146,Nerys,58,174
148 | 147,Quark,61,373
149 | 148,Nerys,39,248
150 | 149,Beverly,49,340
151 | 150,Nerys,55,313
152 | 151,Keiko,54,441
153 | 152,Kasidy,54,235
154 | 153,Morn,63,342
155 | 154,Geordi,40,389
156 | 155,Beverly,50,126
157 | 156,Deanna,44,360
158 | 157,Dukat,34,319
159 | 158,Odo,31,340
160 | 159,Kasidy,67,438
161 | 160,Beverly,58,112
162 | 161,Odo,39,207
163 | 162,Ezri,59,14
164 | 163,Nerys,67,204
165 | 164,Will,31,172
166 | 165,Leeta,26,282
167 | 166,Lwaxana,25,10
168 | 167,Quark,48,57
169 | 168,Martok,68,112
170 | 169,Beverly,53,92
171 | 170,Jean-Luc,68,490
172 | 171,Weyoun,29,126
173 | 172,Kasidy,55,204
174 | 173,Leeta,23,129
175 | 174,Deanna,47,87
176 | 175,Will,38,459
177 | 176,Worf,55,474
178 | 177,Brunt,67,316
179 | 178,Kasidy,26,381
180 | 179,Elim,37,426
181 | 180,Kasidy,30,108
182 | 181,Rom,43,404
183 | 182,Weyoun,26,145
184 | 183,Ben,47,488
185 | 184,Julian,44,84
186 | 185,Weyoun,48,287
187 | 186,Miles,31,109
188 | 187,Nerys,47,225
189 | 188,Keiko,54,369
190 | 189,Quark,62,23
191 | 190,Geordi,60,294
192 | 191,Nog,40,349
193 | 192,Jadzia,45,497
194 | 193,Nerys,60,125
195 | 194,Kasidy,38,2
196 | 195,Ben,30,376
197 | 196,Data,38,173
198 | 197,Leeta,38,76
199 | 198,Brunt,48,381
200 | 199,Hugh,38,180
201 | 200,Kasidy,21,472
202 | 201,Ezri,23,174
203 | 202,Lwaxana,63,469
204 | 203,Ezri,46,125
205 | 204,Deanna,64,164
206 | 205,Morn,69,236
207 | 206,Will,21,491
208 | 207,Lwaxana,41,206
209 | 208,Nog,37,271
210 | 209,Brunt,27,174
211 | 210,Data,33,245
212 | 211,Ben,61,73
213 | 212,Geordi,55,284
214 | 213,Worf,28,312
215 | 214,Miles,32,182
216 | 215,Will,22,6
217 | 216,Brunt,34,116
218 | 217,Keiko,29,260
219 | 218,Gowron,66,350
220 | 219,Lwaxana,26,345
221 | 220,Jean-Luc,41,394
222 | 221,Dukat,27,150
223 | 222,Rom,34,346
224 | 223,Odo,40,406
225 | 224,Keiko,44,277
226 | 225,Elim,19,106
227 | 226,Lwaxana,37,207
228 | 227,Ezri,40,198
229 | 228,Martok,26,293
230 | 229,Gowron,24,150
231 | 230,Beverly,54,397
232 | 231,Ezri,59,42
233 | 232,Worf,68,481
234 | 233,Gowron,67,70
235 | 234,Deanna,49,22
236 | 235,Elim,57,8
237 | 236,Brunt,62,442
238 | 237,Nerys,61,469
239 | 238,Deanna,25,305
240 | 239,Nog,48,345
241 | 240,Deanna,46,154
242 | 241,Quark,45,332
243 | 242,Data,25,101
244 | 243,Martok,61,68
245 | 244,Dukat,21,471
246 | 245,Jean-Luc,28,174
247 | 246,Leeta,41,260
248 | 247,Ezri,52,338
249 | 248,Dukat,21,138
250 | 249,Nerys,66,41
251 | 250,Hugh,36,342
252 | 251,Rom,55,57
253 | 252,Will,36,174
254 | 253,Leeta,69,116
255 | 254,Ezri,67,79
256 | 255,Deanna,60,324
257 | 256,Worf,32,412
258 | 257,Data,51,161
259 | 258,Worf,68,217
260 | 259,Kasidy,29,11
261 | 260,Brunt,38,96
262 | 261,Jadzia,40,172
263 | 262,Will,51,334
264 | 263,Martok,40,33
265 | 264,Julian,29,228
266 | 265,Gowron,27,471
267 | 266,Jean-Luc,66,496
268 | 267,Dukat,49,106
269 | 268,Ezri,26,298
270 | 269,Beverly,55,289
271 | 270,Data,44,353
272 | 271,Morn,25,446
273 | 272,Quark,29,367
274 | 273,Data,51,493
275 | 274,Julian,64,244
276 | 275,Will,47,13
277 | 276,Dukat,54,462
278 | 277,Hugh,46,300
279 | 278,Data,44,499
280 | 279,Beverly,23,133
281 | 280,Nerys,26,492
282 | 281,Worf,21,89
283 | 282,Geordi,32,404
284 | 283,Dukat,65,443
285 | 284,Nog,26,269
286 | 285,Data,43,101
287 | 286,Lwaxana,30,384
288 | 287,Beverly,64,396
289 | 288,Hugh,56,354
290 | 289,Ezri,30,221
291 | 290,Beverly,62,290
292 | 291,Dukat,23,373
293 | 292,Nog,63,380
294 | 293,Deanna,23,65
295 | 294,Leeta,38,410
296 | 295,Nerys,40,56
297 | 296,Data,38,454
298 | 297,Ben,45,395
299 | 298,Guinan,57,207
300 | 299,Rom,57,311
301 | 300,Beverly,49,147
302 | 301,Weyoun,28,108
303 | 302,Beverly,37,263
304 | 303,Deanna,46,319
305 | 304,Will,19,404
306 | 305,Quark,29,182
307 | 306,Beverly,23,323
308 | 307,Keiko,41,340
309 | 308,Morn,45,59
310 | 309,Geordi,67,153
311 | 310,Odo,68,189
312 | 311,Martok,43,48
313 | 312,Jadzia,61,421
314 | 313,Dukat,59,169
315 | 314,Geordi,36,168
316 | 315,Weyoun,25,208
317 | 316,Hugh,64,391
318 | 317,Guinan,59,439
319 | 318,Deanna,35,251
320 | 319,Leeta,30,476
321 | 320,Worf,62,450
322 | 321,Data,44,61
323 | 322,Rom,58,92
324 | 323,Nog,29,236
325 | 324,Miles,56,343
326 | 325,Keiko,51,492
327 | 326,Beverly,46,407
328 | 327,Julian,20,63
329 | 328,Deanna,62,41
330 | 329,Dukat,67,35
331 | 330,Ezri,33,356
332 | 331,Martok,30,17
333 | 332,Julian,55,362
334 | 333,Ben,29,207
335 | 334,Leeta,40,7
336 | 335,Odo,27,337
337 | 336,Gowron,47,4
338 | 337,Miles,58,10
339 | 338,Will,28,180
340 | 339,Morn,66,305
341 | 340,Nerys,57,275
342 | 341,Data,18,326
343 | 342,Guinan,46,151
344 | 343,Odo,26,254
345 | 344,Data,30,487
346 | 345,Ezri,31,394
347 | 346,Hugh,29,329
348 | 347,Geordi,32,24
349 | 348,Weyoun,33,460
350 | 349,Kasidy,20,277
351 | 350,Nog,55,464
352 | 351,Keiko,54,72
353 | 352,Deanna,27,53
354 | 353,Julian,64,499
355 | 354,Kasidy,69,15
356 | 355,Keiko,46,352
357 | 356,Weyoun,67,149
358 | 357,Brunt,26,7
359 | 358,Will,52,276
360 | 359,Nog,54,442
361 | 360,Nerys,39,68
362 | 361,Worf,68,206
363 | 362,Ezri,39,120
364 | 363,Dukat,41,397
365 | 364,Lwaxana,54,115
366 | 365,Brunt,65,430
367 | 366,Keiko,19,119
368 | 367,Data,39,106
369 | 368,Elim,26,383
370 | 369,Quark,48,266
371 | 370,Jadzia,53,86
372 | 371,Guinan,31,435
373 | 372,Brunt,62,273
374 | 373,Quark,19,272
375 | 374,Nog,68,293
376 | 375,Hugh,66,201
377 | 376,Gowron,23,392
378 | 377,Beverly,18,418
379 | 378,Guinan,47,97
380 | 379,Data,60,304
381 | 380,Brunt,35,65
382 | 381,Nog,38,95
383 | 382,Worf,66,240
384 | 383,Data,69,148
385 | 384,Martok,67,355
386 | 385,Beverly,57,436
387 | 386,Data,35,428
388 | 387,Will,43,335
389 | 388,Nog,30,184
390 | 389,Weyoun,38,38
391 | 390,Martok,22,266
392 | 391,Ben,64,309
393 | 392,Data,64,343
394 | 393,Quark,50,436
395 | 394,Keiko,23,230
396 | 395,Jean-Luc,56,15
397 | 396,Keiko,67,38
398 | 397,Quark,69,470
399 | 398,Lwaxana,26,124
400 | 399,Beverly,24,401
401 | 400,Data,29,128
402 | 401,Jean-Luc,42,467
403 | 402,Hugh,58,98
404 | 403,Weyoun,21,224
405 | 404,Kasidy,18,24
406 | 405,Nog,56,371
407 | 406,Ben,57,121
408 | 407,Miles,36,68
409 | 408,Dukat,62,496
410 | 409,Nog,19,267
411 | 410,Odo,35,299
412 | 411,Lwaxana,58,22
413 | 412,Jadzia,53,451
414 | 413,Hugh,45,147
415 | 414,Martok,56,313
416 | 415,Quark,30,65
417 | 416,Nerys,33,294
418 | 417,Julian,37,106
419 | 418,Guinan,32,212
420 | 419,Kasidy,55,176
421 | 420,Jadzia,26,391
422 | 421,Will,40,261
423 | 422,Ben,67,292
424 | 423,Will,44,388
425 | 424,Keiko,55,470
426 | 425,Quark,33,243
427 | 426,Worf,24,77
428 | 427,Brunt,28,258
429 | 428,Lwaxana,68,423
430 | 429,Jean-Luc,63,345
431 | 430,Geordi,36,493
432 | 431,Quark,36,343
433 | 432,Brunt,45,54
434 | 433,Ezri,38,203
435 | 434,Deanna,57,289
436 | 435,Guinan,42,275
437 | 436,Geordi,57,229
438 | 437,Morn,59,221
439 | 438,Nog,42,95
440 | 439,Data,18,417
441 | 440,Elim,48,394
442 | 441,Jadzia,38,143
443 | 442,Nog,46,105
444 | 443,Geordi,64,175
445 | 444,Keiko,18,472
446 | 445,Guinan,40,286
447 | 446,Quark,32,41
448 | 447,Julian,38,34
449 | 448,Nerys,48,439
450 | 449,Data,52,419
451 | 450,Weyoun,37,234
452 | 451,Martok,28,34
453 | 452,Ezri,58,6
454 | 453,Julian,44,337
455 | 454,Weyoun,52,456
456 | 455,Elim,33,463
457 | 456,Ezri,37,471
458 | 457,Worf,51,81
459 | 458,Elim,44,335
460 | 459,Geordi,26,84
461 | 460,Hugh,47,400
462 | 461,Geordi,41,236
463 | 462,Nerys,23,287
464 | 463,Keiko,40,220
465 | 464,Beverly,25,485
466 | 465,Morn,53,126
467 | 466,Brunt,33,228
468 | 467,Weyoun,42,194
469 | 468,Ezri,46,227
470 | 469,Brunt,55,271
471 | 470,Deanna,38,160
472 | 471,Brunt,52,273
473 | 472,Nog,27,154
474 | 473,Morn,35,38
475 | 474,Keiko,34,48
476 | 475,Ben,52,446
477 | 476,Jean-Luc,28,378
478 | 477,Gowron,50,119
479 | 478,Dukat,41,62
480 | 479,Kasidy,44,320
481 | 480,Geordi,43,428
482 | 481,Elim,32,97
483 | 482,Ben,48,146
484 | 483,Hugh,57,99
485 | 484,Leeta,22,478
486 | 485,Rom,47,356
487 | 486,Elim,49,17
488 | 487,Brunt,69,431
489 | 488,Nog,61,103
490 | 489,Odo,33,410
491 | 490,Nerys,65,101
492 | 491,Rom,60,2
493 | 492,Dukat,19,36
494 | 493,Hugh,23,357
495 | 494,Kasidy,18,194
496 | 495,Data,46,155
497 | 496,Gowron,39,275
498 | 497,Lwaxana,34,423
499 | 498,Jadzia,62,36
500 | 499,Leeta,62,12
501 | 


--------------------------------------------------------------------------------
/friends-by-age.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("FriendsByAge")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | def parseLine(line):
 7 |     fields = line.split(',')
 8 |     age = int(fields[2])
 9 |     numFriends = int(fields[3])
10 |     return (age, numFriends)
11 | 
12 | lines = sc.textFile("file:///SparkCourse/fakefriends.csv")
13 | rdd = lines.map(parseLine)
14 | totalsByAge = rdd.mapValues(lambda x: (x, 1)).reduceByKey(lambda x, y: (x[0] + y[0], x[1] + y[1]))
15 | averagesByAge = totalsByAge.mapValues(lambda x: x[0] / x[1])
16 | results = averagesByAge.collect()
17 | for result in results:
18 |     print(result)
19 | 


--------------------------------------------------------------------------------
/max-temperatures.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("MaxTemperatures")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | def parseLine(line):
 7 |     fields = line.split(',')
 8 |     stationID = fields[0]
 9 |     entryType = fields[2]
10 |     temperature = float(fields[3]) * 0.1 * (9.0 / 5.0) + 32.0
11 |     return (stationID, entryType, temperature)
12 | 
13 | lines = sc.textFile("file:///SparkCourse/1800.csv")
14 | parsedLines = lines.map(parseLine)
15 | maxTemps = parsedLines.filter(lambda x: "TMAX" in x[1])
16 | stationTemps = maxTemps.map(lambda x: (x[0], x[2]))
17 | maxTemps = stationTemps.reduceByKey(lambda x, y: max(x,y))
18 | results = maxTemps.collect();
19 | 
20 | for result in results:
21 |     print(result[0] + "\t{:.2f}F".format(result[1]))
22 | 


--------------------------------------------------------------------------------
/min-temperatures.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("MinTemperatures")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | def parseLine(line):
 7 |     fields = line.split(',')
 8 |     stationID = fields[0]
 9 |     entryType = fields[2]
10 |     temperature = float(fields[3]) * 0.1 * (9.0 / 5.0) + 32.0
11 |     return (stationID, entryType, temperature)
12 | 
13 | lines = sc.textFile("file:///SparkCourse/1800.csv")
14 | parsedLines = lines.map(parseLine)
15 | minTemps = parsedLines.filter(lambda x: "TMIN" in x[1])
16 | stationTemps = minTemps.map(lambda x: (x[0], x[2]))
17 | minTemps = stationTemps.reduceByKey(lambda x, y: min(x,y))
18 | results = minTemps.collect();
19 | 
20 | for result in results:
21 |     print(result[0] + "\t{:.2f}F".format(result[1]))
22 | 


--------------------------------------------------------------------------------
/most-popular-superhero.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("PopularHero")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | def countCoOccurences(line):
 7 |     elements = line.split()
 8 |     return (int(elements[0]), len(elements) - 1)
 9 | 
10 | def parseNames(line):
11 |     fields = line.split('\"')
12 |     return (int(fields[0]), fields[1].encode("utf8"))
13 | 
14 | names = sc.textFile("file:///SparkCourse/marvel-names.txt")
15 | namesRdd = names.map(parseNames)
16 | 
17 | lines = sc.textFile("file:///SparkCourse/marvel-graph.txt")
18 | 
19 | pairings = lines.map(countCoOccurences)
20 | totalFriendsByCharacter = pairings.reduceByKey(lambda x, y : x + y)
21 | flipped = totalFriendsByCharacter.map(lambda (x,y) : (y,x))
22 | 
23 | mostPopular = flipped.max()
24 | 
25 | mostPopularName = namesRdd.lookup(mostPopular[1])[0]
26 | 
27 | print(mostPopularName + " is the most popular superhero, with " + \
28 |     str(mostPopular[0]) + " co-appearances.")
29 | 


--------------------------------------------------------------------------------
/movie-recommendations-als-1m.py:
--------------------------------------------------------------------------------
 1 | import sys
 2 | from pyspark import SparkConf, SparkContext
 3 | from pyspark.mllib.recommendation import ALS, Rating
 4 | 
 5 | def loadMovieNames():
 6 |     movieNames = {}
 7 |     with open("ml-1m/movies.dat") as f:
 8 |         for line in f:
 9 |             fields = line.split('::')
10 |             movieNames[int(fields[0])] = fields[1].decode('ascii', 'ignore')
11 |     return movieNames
12 | 
13 | conf = SparkConf().setMaster("local[*]").setAppName("MovieRecommendationsALS")
14 | sc = SparkContext(conf = conf)
15 | sc.setCheckpointDir('checkpoint')
16 | 
17 | print("\nLoading movie names...")
18 | nameDict = loadMovieNames()
19 | 
20 | data = sc.textFile("file:///E:/SparkCourse/ml-1m/ratings.dat")
21 | 
22 | ratings = data.map(lambda l: l.split("::")).map(lambda l: Rating(int(l[0]), int(l[1]), float(l[2]))).cache()
23 | 
24 | # Build the recommendation model using Alternating Least Squares
25 | print("\nTraining recommendation model...")
26 | rank = 10
27 | numIterations = 20
28 | model = ALS.train(ratings, rank, numIterations)
29 | 
30 | userID = int(sys.argv[1])
31 | 
32 | print("\nRatings for user ID " + str(userID) + ":")
33 | userRatings = ratings.filter(lambda l: l[0] == userID)
34 | for rating in userRatings.collect():
35 |     print(nameDict[int(rating[1])] + ": " + str(rating[2]))
36 | 
37 | print("\nTop 10 recommendations:")
38 | recommendations = model.recommendProducts(userID, 10)
39 | for recommendation in recommendations:
40 |     print(nameDict[int(recommendation[1])] + \
41 |         " score " + str(recommendation[2]))
42 | 


--------------------------------------------------------------------------------
/movie-recommendations-als.py:
--------------------------------------------------------------------------------
 1 | import sys
 2 | from pyspark import SparkConf, SparkContext
 3 | from pyspark.mllib.recommendation import ALS, Rating
 4 | 
 5 | def loadMovieNames():
 6 |     movieNames = {}
 7 |     with open("ml-100k/u.ITEM") as f:
 8 |         for line in f:
 9 |             fields = line.split('|')
10 |             movieNames[int(fields[0])] = fields[1].decode('ascii', 'ignore')
11 |     return movieNames
12 | 
13 | conf = SparkConf().setMaster("local[*]").setAppName("MovieRecommendationsALS")
14 | sc = SparkContext(conf = conf)
15 | sc.setCheckpointDir('checkpoint')
16 | 
17 | print("\nLoading movie names...")
18 | nameDict = loadMovieNames()
19 | 
20 | data = sc.textFile("file:///SparkCourse/ml-100k/u.data")
21 | 
22 | ratings = data.map(lambda l: l.split()).map(lambda l: Rating(int(l[0]), int(l[1]), float(l[2]))).cache()
23 | 
24 | # Build the recommendation model using Alternating Least Squares
25 | print("\nTraining recommendation model...")
26 | rank = 10
27 | # Lowered numIterations to ensure it works on lower-end systems
28 | numIterations = 6
29 | model = ALS.train(ratings, rank, numIterations)
30 | 
31 | userID = int(sys.argv[1])
32 | 
33 | print("\nRatings for user ID " + str(userID) + ":")
34 | userRatings = ratings.filter(lambda l: l[0] == userID)
35 | for rating in userRatings.collect():
36 |     print nameDict[int(rating[1])] + ": " + str(rating[2])
37 | 
38 | print("\nTop 10 recommendations:")
39 | recommendations = model.recommendProducts(userID, 10)
40 | for recommendation in recommendations:
41 |     print nameDict[int(recommendation[1])] + \
42 |         " score " + str(recommendation[2])
43 | 


--------------------------------------------------------------------------------
/movie-similarities-1m.py:
--------------------------------------------------------------------------------
  1 | import sys
  2 | from pyspark import SparkConf, SparkContext
  3 | from math import sqrt
  4 | 
  5 | #To run on EMR successfully + output results for Star Wars:
  6 | #aws s3 cp s3://sundog-spark/MovieSimilarities1M.py ./
  7 | #aws s3 sp c3://sundog-spark/ml-1m/movies.dat ./
  8 | #spark-submit --executor-memory 1g MovieSimilarities1M.py 260
  9 | 
 10 | def loadMovieNames():
 11 |     movieNames = {}
 12 |     with open("movies.dat") as f:
 13 |         for line in f:
 14 |             fields = line.split("::")
 15 |             movieNames[int(fields[0])] = fields[1].decode('ascii', 'ignore')
 16 |     return movieNames
 17 | 
 18 | def makePairs((user, ratings)):
 19 |     (movie1, rating1) = ratings[0]
 20 |     (movie2, rating2) = ratings[1]
 21 |     return ((movie1, movie2), (rating1, rating2))
 22 | 
 23 | def filterDuplicates( (userID, ratings) ):
 24 |     (movie1, rating1) = ratings[0]
 25 |     (movie2, rating2) = ratings[1]
 26 |     return movie1 < movie2
 27 | 
 28 | def computeCosineSimilarity(ratingPairs):
 29 |     numPairs = 0
 30 |     sum_xx = sum_yy = sum_xy = 0
 31 |     for ratingX, ratingY in ratingPairs:
 32 |         sum_xx += ratingX * ratingX
 33 |         sum_yy += ratingY * ratingY
 34 |         sum_xy += ratingX * ratingY
 35 |         numPairs += 1
 36 | 
 37 |     numerator = sum_xy
 38 |     denominator = sqrt(sum_xx) * sqrt(sum_yy)
 39 | 
 40 |     score = 0
 41 |     if (denominator):
 42 |         score = (numerator / (float(denominator)))
 43 | 
 44 |     return (score, numPairs)
 45 | 
 46 | 
 47 | conf = SparkConf()
 48 | sc = SparkContext(conf = conf)
 49 | 
 50 | print("\nLoading movie names...")
 51 | nameDict = loadMovieNames()
 52 | 
 53 | data = sc.textFile("s3n://sundog-spark/ml-1m/ratings.dat")
 54 | 
 55 | # Map ratings to key / value pairs: user ID => movie ID, rating
 56 | ratings = data.map(lambda l: l.split("::")).map(lambda l: (int(l[0]), (int(l[1]), float(l[2]))))
 57 | 
 58 | # Emit every movie rated together by the same user.
 59 | # Self-join to find every combination.
 60 | ratingsPartitioned = ratings.partitionBy(100)
 61 | joinedRatings = ratingsPartitioned.join(ratingsPartitioned)
 62 | 
 63 | # At this point our RDD consists of userID => ((movieID, rating), (movieID, rating))
 64 | 
 65 | # Filter out duplicate pairs
 66 | uniqueJoinedRatings = joinedRatings.filter(filterDuplicates)
 67 | 
 68 | # Now key by (movie1, movie2) pairs.
 69 | moviePairs = uniqueJoinedRatings.map(makePairs).partitionBy(100)
 70 | 
 71 | # We now have (movie1, movie2) => (rating1, rating2)
 72 | # Now collect all ratings for each movie pair and compute similarity
 73 | moviePairRatings = moviePairs.groupByKey()
 74 | 
 75 | # We now have (movie1, movie2) = > (rating1, rating2), (rating1, rating2) ...
 76 | # Can now compute similarities.
 77 | moviePairSimilarities = moviePairRatings.mapValues(computeCosineSimilarity).persist()
 78 | 
 79 | # Save the results if desired
 80 | moviePairSimilarities.sortByKey()
 81 | moviePairSimilarities.saveAsTextFile("movie-sims")
 82 | 
 83 | # Extract similarities for the movie we care about that are "good".
 84 | if (len(sys.argv) > 1):
 85 | 
 86 |     scoreThreshold = 0.97
 87 |     coOccurenceThreshold = 1000
 88 | 
 89 |     movieID = int(sys.argv[1])
 90 | 
 91 |     # Filter for movies with this sim that are "good" as defined by
 92 |     # our quality thresholds above
 93 |     filteredResults = moviePairSimilarities.filter(lambda((pair,sim)): \
 94 |         (pair[0] == movieID or pair[1] == movieID) \
 95 |         and sim[0] > scoreThreshold and sim[1] > coOccurenceThreshold)
 96 | 
 97 |     # Sort by quality score.
 98 |     results = filteredResults.map(lambda((pair,sim)): (sim, pair)).sortByKey(ascending = False).take(10)
 99 | 
100 |     print("Top 10 similar movies for " + nameDict[movieID])
101 |     for result in results:
102 |         (sim, pair) = result
103 |         # Display the similarity result that isn't the movie we're looking at
104 |         similarMovieID = pair[0]
105 |         if (similarMovieID == movieID):
106 |             similarMovieID = pair[1]
107 |         print(nameDict[similarMovieID] + "\tscore: " + str(sim[0]) + "\tstrength: " + str(sim[1]))
108 | 


--------------------------------------------------------------------------------
/movie-similarities-cluster.py:
--------------------------------------------------------------------------------
  1 | import sys
  2 | from pyspark import SparkConf, SparkContext
  3 | from math import sqrt
  4 | 
  5 | def loadMovieNames():
  6 |     movieNames = {}
  7 |     with open("u.ITEM") as f:
  8 |         for line in f:
  9 |             fields = line.split('|')
 10 |             movieNames[int(fields[0])] = fields[1].decode('ascii', 'ignore')
 11 |     return movieNames
 12 | 
 13 | def makePairs((user, ratings)):
 14 |     (movie1, rating1) = ratings[0]
 15 |     (movie2, rating2) = ratings[1]
 16 |     return ((movie1, movie2), (rating1, rating2))
 17 | 
 18 | def filterDuplicates( (userID, ratings) ):
 19 |     (movie1, rating1) = ratings[0]
 20 |     (movie2, rating2) = ratings[1]
 21 |     return movie1 < movie2
 22 | 
 23 | def computeCosineSimilarity(ratingPairs):
 24 |     numPairs = 0
 25 |     sum_xx = sum_yy = sum_xy = 0
 26 |     for ratingX, ratingY in ratingPairs:
 27 |         sum_xx += ratingX * ratingX
 28 |         sum_yy += ratingY * ratingY
 29 |         sum_xy += ratingX * ratingY
 30 |         numPairs += 1
 31 | 
 32 |     numerator = sum_xy
 33 |     denominator = sqrt(sum_xx) * sqrt(sum_yy)
 34 | 
 35 |     score = 0
 36 |     if (denominator):
 37 |         score = (numerator / (float(denominator)))
 38 | 
 39 |     return (score, numPairs)
 40 | 
 41 | 
 42 | conf = SparkConf().setMaster("local[*]").setAppName("MovieSimilarities")
 43 | sc = SparkContext(conf = conf)
 44 | 
 45 | print("\nLoading movie names...")
 46 | nameDict = loadMovieNames()
 47 | 
 48 | data = sc.textFile("s3://sundog-spark/ml-100k/u.data")
 49 | 
 50 | # Map ratings to key / value pairs: user ID => movie ID, rating
 51 | ratings = data.map(lambda l: l.split()).map(lambda l: (int(l[0]), (int(l[1]), float(l[2]))))
 52 | 
 53 | # Emit every movie rated together by the same user.
 54 | # Self-join to find every combination.
 55 | joinedRatings = ratings.join(ratings)
 56 | 
 57 | # At this point our RDD consists of userID => ((movieID, rating), (movieID, rating))
 58 | 
 59 | # Filter out duplicate pairs
 60 | uniqueJoinedRatings = joinedRatings.filter(filterDuplicates)
 61 | 
 62 | # Now key by (movie1, movie2) pairs.
 63 | moviePairs = uniqueJoinedRatings.map(makePairs)
 64 | 
 65 | # We now have (movie1, movie2) => (rating1, rating2)
 66 | # Now collect all ratings for each movie pair and compute similarity
 67 | moviePairRatings = moviePairs.groupByKey()
 68 | 
 69 | # We now have (movie1, movie2) = > (rating1, rating2), (rating1, rating2) ...
 70 | # Can now compute similarities.
 71 | moviePairSimilarities = moviePairRatings.mapValues(computeCosineSimilarity).cache()
 72 | 
 73 | # Save the results if desired
 74 | #moviePairSimilarities.sortByKey()
 75 | #moviePairSimilarities.saveAsTextFile("movie-sims")
 76 | 
 77 | # Extract similarities for the movie we care about that are "good".
 78 | if (len(sys.argv) > 1):
 79 | 
 80 |     scoreThreshold = 0.97
 81 |     coOccurenceThreshold = 50
 82 | 
 83 |     movieID = int(sys.argv[1])
 84 | 
 85 |     # Filter for movies with this sim that are "good" as defined by
 86 |     # our quality thresholds above
 87 |     filteredResults = moviePairSimilarities.filter(lambda((pair,sim)): \
 88 |         (pair[0] == movieID or pair[1] == movieID) \
 89 |         and sim[0] > scoreThreshold and sim[1] > coOccurenceThreshold)
 90 | 
 91 |     # Sort by quality score.
 92 |     results = filteredResults.map(lambda((pair,sim)): (sim, pair)).sortByKey(ascending = False).take(10)
 93 | 
 94 |     print("Top 10 similar movies for " + nameDict[movieID])
 95 |     for result in results:
 96 |         (sim, pair) = result
 97 |         # Display the similarity result that isn't the movie we're looking at
 98 |         similarMovieID = pair[0]
 99 |         if (similarMovieID == movieID):
100 |             similarMovieID = pair[1]
101 |         print(nameDict[similarMovieID] + "\tscore: " + str(sim[0]) + "\tstrength: " + str(sim[1]))
102 | 


--------------------------------------------------------------------------------
/movie-similarities.py:
--------------------------------------------------------------------------------
  1 | import sys
  2 | from pyspark import SparkConf, SparkContext
  3 | from math import sqrt
  4 | 
  5 | def loadMovieNames():
  6 |     movieNames = {}
  7 |     with open("ml-100k/u.ITEM") as f:
  8 |         for line in f:
  9 |             fields = line.split('|')
 10 |             movieNames[int(fields[0])] = fields[1].decode('ascii', 'ignore')
 11 |     return movieNames
 12 | 
 13 | def makePairs((user, ratings)):
 14 |     (movie1, rating1) = ratings[0]
 15 |     (movie2, rating2) = ratings[1]
 16 |     return ((movie1, movie2), (rating1, rating2))
 17 | 
 18 | def filterDuplicates( (userID, ratings) ):
 19 |     (movie1, rating1) = ratings[0]
 20 |     (movie2, rating2) = ratings[1]
 21 |     return movie1 < movie2
 22 | 
 23 | def computeCosineSimilarity(ratingPairs):
 24 |     numPairs = 0
 25 |     sum_xx = sum_yy = sum_xy = 0
 26 |     for ratingX, ratingY in ratingPairs:
 27 |         sum_xx += ratingX * ratingX
 28 |         sum_yy += ratingY * ratingY
 29 |         sum_xy += ratingX * ratingY
 30 |         numPairs += 1
 31 | 
 32 |     numerator = sum_xy
 33 |     denominator = sqrt(sum_xx) * sqrt(sum_yy)
 34 | 
 35 |     score = 0
 36 |     if (denominator):
 37 |         score = (numerator / (float(denominator)))
 38 | 
 39 |     return (score, numPairs)
 40 | 
 41 | 
 42 | conf = SparkConf().setMaster("local[*]").setAppName("MovieSimilarities")
 43 | sc = SparkContext(conf = conf)
 44 | 
 45 | print("\nLoading movie names...")
 46 | nameDict = loadMovieNames()
 47 | 
 48 | data = sc.textFile("file:///SparkCourse/ml-100k/u.data")
 49 | 
 50 | # Map ratings to key / value pairs: user ID => movie ID, rating
 51 | ratings = data.map(lambda l: l.split()).map(lambda l: (int(l[0]), (int(l[1]), float(l[2]))))
 52 | 
 53 | # Emit every movie rated together by the same user.
 54 | # Self-join to find every combination.
 55 | joinedRatings = ratings.join(ratings)
 56 | 
 57 | # At this point our RDD consists of userID => ((movieID, rating), (movieID, rating))
 58 | 
 59 | # Filter out duplicate pairs
 60 | uniqueJoinedRatings = joinedRatings.filter(filterDuplicates)
 61 | 
 62 | # Now key by (movie1, movie2) pairs.
 63 | moviePairs = uniqueJoinedRatings.map(makePairs)
 64 | 
 65 | # We now have (movie1, movie2) => (rating1, rating2)
 66 | # Now collect all ratings for each movie pair and compute similarity
 67 | moviePairRatings = moviePairs.groupByKey()
 68 | 
 69 | # We now have (movie1, movie2) = > (rating1, rating2), (rating1, rating2) ...
 70 | # Can now compute similarities.
 71 | moviePairSimilarities = moviePairRatings.mapValues(computeCosineSimilarity).cache()
 72 | 
 73 | # Save the results if desired
 74 | #moviePairSimilarities.sortByKey()
 75 | #moviePairSimilarities.saveAsTextFile("movie-sims")
 76 | 
 77 | # Extract similarities for the movie we care about that are "good".
 78 | if (len(sys.argv) > 1):
 79 | 
 80 |     scoreThreshold = 0.97
 81 |     coOccurenceThreshold = 50
 82 | 
 83 |     movieID = int(sys.argv[1])
 84 | 
 85 |     # Filter for movies with this sim that are "good" as defined by
 86 |     # our quality thresholds above
 87 |     filteredResults = moviePairSimilarities.filter(lambda((pair,sim)): \
 88 |         (pair[0] == movieID or pair[1] == movieID) \
 89 |         and sim[0] > scoreThreshold and sim[1] > coOccurenceThreshold)
 90 | 
 91 |     # Sort by quality score.
 92 |     results = filteredResults.map(lambda((pair,sim)): (sim, pair)).sortByKey(ascending = False).take(10)
 93 | 
 94 |     print("Top 10 similar movies for " + nameDict[movieID])
 95 |     for result in results:
 96 |         (sim, pair) = result
 97 |         # Display the similarity result that isn't the movie we're looking at
 98 |         similarMovieID = pair[0]
 99 |         if (similarMovieID == movieID):
100 |             similarMovieID = pair[1]
101 |         print(nameDict[similarMovieID] + "\tscore: " + str(sim[0]) + "\tstrength: " + str(sim[1]))
102 | 


--------------------------------------------------------------------------------
/popular-movies-dataframe.py:
--------------------------------------------------------------------------------
 1 | from pyspark.sql import SparkSession
 2 | from pyspark.sql import Row
 3 | from pyspark.sql import functions
 4 | 
 5 | def loadMovieNames():
 6 |     movieNames = {}
 7 |     with open("ml-100k/u.ITEM") as f:
 8 |         for line in f:
 9 |             fields = line.split('|')
10 |             movieNames[int(fields[0])] = fields[1]
11 |     return movieNames
12 | 
13 | # Create a SparkSession (the config bit is only for Windows!)
14 | spark = SparkSession.builder.config("spark.sql.warehouse.dir", "file:///C:/temp").appName("PopularMovies").getOrCreate()
15 | 
16 | # Load up our movie ID -> name dictionary
17 | nameDict = loadMovieNames()
18 | 
19 | # Get the raw data
20 | lines = spark.sparkContext.textFile("file:///SparkCourse/ml-100k/u.data")
21 | # Convert it to a RDD of Row objects
22 | movies = lines.map(lambda x: Row(movieID =int(x.split()[1])))
23 | # Convert that to a DataFrame
24 | movieDataset = spark.createDataFrame(movies)
25 | 
26 | # Some SQL-style magic to sort all movies by popularity in one line!
27 | topMovieIDs = movieDataset.groupBy("movieID").count().orderBy("count", ascending=False).cache()
28 | 
29 | # Show the results at this point:
30 | 
31 | #|movieID|count|
32 | #+-------+-----+
33 | #|     50|  584|
34 | #|    258|  509|
35 | #|    100|  508|
36 | 
37 | topMovieIDs.show()
38 | 
39 | # Grab the top 10
40 | top10 = topMovieIDs.take(10)
41 | 
42 | # Print the results
43 | print("\n")
44 | for result in top10:
45 |     # Each row has movieID, count as above.
46 |     print("%s: %d" % (nameDict[result[0]], result[1]))
47 | 
48 | # Stop the session
49 | spark.stop()
50 | 


--------------------------------------------------------------------------------
/popular-movies-nicer.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | def loadMovieNames():
 4 |     movieNames = {}
 5 |     with open("ml-100k/u.ITEM") as f:
 6 |         for line in f:
 7 |             fields = line.split('|')
 8 |             movieNames[int(fields[0])] = fields[1]
 9 |     return movieNames
10 | 
11 | conf = SparkConf().setMaster("local").setAppName("PopularMovies")
12 | sc = SparkContext(conf = conf)
13 | 
14 | nameDict = sc.broadcast(loadMovieNames())
15 | 
16 | lines = sc.textFile("file:///SparkCourse/ml-100k/u.data")
17 | movies = lines.map(lambda x: (int(x.split()[1]), 1))
18 | movieCounts = movies.reduceByKey(lambda x, y: x + y)
19 | 
20 | flipped = movieCounts.map( lambda (x, y) : (y, x))
21 | sortedMovies = flipped.sortByKey()
22 | 
23 | sortedMoviesWithNames = sortedMovies.map(lambda (count, movie) : (nameDict.value[movie], count))
24 | 
25 | results = sortedMoviesWithNames.collect()
26 | 
27 | for result in results:
28 |     print(result)
29 | 


--------------------------------------------------------------------------------
/popular-movies.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("PopularMovies")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | lines = sc.textFile("file:///SparkCourse/ml-100k/u.data")
 7 | movies = lines.map(lambda x: (int(x.split()[1]), 1))
 8 | movieCounts = movies.reduceByKey(lambda x, y: x + y)
 9 | 
10 | flipped = movieCounts.map( lambda (x, y) : (y, x) )
11 | sortedMovies = flipped.sortByKey()
12 | 
13 | results = sortedMovies.collect()
14 | 
15 | for result in results:
16 |     print(result)
17 | 


--------------------------------------------------------------------------------
/ratings-counter.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | import collections
 3 | 
 4 | conf = SparkConf().setMaster("local").setAppName("RatingsHistogram")
 5 | sc = SparkContext(conf = conf)
 6 | 
 7 | lines = sc.textFile("file:///SparkCourse/ml-100k/u.data")
 8 | ratings = lines.map(lambda x: x.split()[2])
 9 | result = ratings.countByValue()
10 | 
11 | sortedResults = collections.OrderedDict(sorted(result.items()))
12 | for key, value in sortedResults.items():
13 |     print("%s %i" % (key, value))
14 | 


--------------------------------------------------------------------------------
/regression.txt:
--------------------------------------------------------------------------------
   1 | -1.74,1.66
   2 | 1.24,-1.18
   3 | 0.29,-0.40
   4 | -0.13,0.09
   5 | -0.39,0.38
   6 | -1.79,1.73
   7 | 0.71,-0.77
   8 | 1.39,-1.48
   9 | 1.15,-1.43
  10 | 0.13,-0.07
  11 | 0.05,-0.07
  12 | 1.90,-1.80
  13 | 1.48,-1.42
  14 | 0.32,-0.30
  15 | -1.11,1.00
  16 | 0.51,-0.62
  17 | -1.58,1.45
  18 | -0.46,0.44
  19 | -0.49,0.37
  20 | 0.31,-0.30
  21 | 0.85,-0.77
  22 | 0.61,-0.69
  23 | -0.66,0.65
  24 | 0.99,-0.94
  25 | -0.73,0.62
  26 | 0.43,-0.42
  27 | -0.50,0.35
  28 | -1.77,1.66
  29 | -0.65,0.88
  30 | -2.29,2.35
  31 | 0.74,-0.66
  32 | 0.44,-0.44
  33 | -0.41,0.51
  34 | 0.40,-0.36
  35 | -2.17,2.19
  36 | 1.27,-1.11
  37 | -0.94,1.00
  38 | -0.59,0.66
  39 | -0.04,0.01
  40 | 0.70,-0.89
  41 | -0.85,0.80
  42 | -0.14,0.02
  43 | 0.18,-0.18
  44 | 1.20,-1.15
  45 | 0.98,-0.91
  46 | 0.08,0.04
  47 | -0.33,0.39
  48 | -1.12,1.10
  49 | 0.08,-0.10
  50 | -0.99,1.09
  51 | -1.94,1.98
  52 | 0.18,-0.15
  53 | 0.44,-0.37
  54 | -0.74,0.93
  55 | 2.39,-2.40
  56 | -1.91,1.86
  57 | -0.07,-0.09
  58 | -2.00,2.02
  59 | -0.36,0.56
  60 | -0.52,0.69
  61 | 0.72,-0.81
  62 | 0.69,-0.73
  63 | 1.54,-1.49
  64 | -2.26,2.25
  65 | 2.33,-2.15
  66 | 0.00,-0.07
  67 | -1.30,1.45
  68 | 1.11,-1.16
  69 | -0.23,0.29
  70 | -0.14,0.13
  71 | -0.04,0.13
  72 | 1.05,-0.80
  73 | -1.22,1.20
  74 | 0.76,-0.77
  75 | 2.17,-2.02
  76 | 0.82,-0.96
  77 | 0.34,-0.36
  78 | -1.61,1.72
  79 | 0.74,-0.64
  80 | 0.11,-0.09
  81 | -1.40,1.32
  82 | 0.21,-0.23
  83 | -1.96,1.98
  84 | 0.75,-0.92
  85 | -0.59,0.63
  86 | -1.39,1.32
  87 | -1.26,1.17
  88 | -0.53,0.50
  89 | -1.10,0.92
  90 | 0.55,-0.68
  91 | 0.39,-0.42
  92 | -1.48,1.38
  93 | 0.53,-0.56
  94 | -0.96,1.06
  95 | -1.30,1.14
  96 | 0.84,-0.84
  97 | -1.16,1.25
  98 | 0.02,-0.05
  99 | 0.93,-0.79
 100 | 0.97,-0.98
 101 | -0.65,0.54
 102 | -2.07,2.04
 103 | 1.28,-1.27
 104 | 0.72,-0.81
 105 | -1.65,1.63
 106 | -0.07,-0.01
 107 | -2.12,1.90
 108 | -1.01,0.92
 109 | 1.06,-1.11
 110 | -0.68,0.76
 111 | 1.32,-1.49
 112 | -1.05,1.00
 113 | -1.25,1.20
 114 | -0.49,0.44
 115 | 0.11,-0.07
 116 | -1.59,1.62
 117 | 0.14,-0.14
 118 | -0.24,0.27
 119 | -0.85,0.91
 120 | 1.19,-1.21
 121 | 1.51,-1.61
 122 | -1.30,1.18
 123 | 0.17,-0.09
 124 | 0.03,-0.04
 125 | -0.35,0.26
 126 | 0.21,-0.23
 127 | -1.42,1.59
 128 | 1.28,-1.26
 129 | -0.27,0.16
 130 | 0.26,-0.28
 131 | 1.55,-1.23
 132 | -0.05,0.06
 133 | 0.37,-0.33
 134 | -1.29,1.47
 135 | -0.76,0.84
 136 | 0.10,0.02
 137 | 0.00,0.14
 138 | -0.50,0.56
 139 | -0.05,0.06
 140 | -0.65,0.57
 141 | 0.41,-0.39
 142 | 0.09,-0.04
 143 | -1.91,1.83
 144 | 0.81,-0.65
 145 | -0.30,0.42
 146 | 0.18,-0.09
 147 | 0.61,-0.48
 148 | 0.76,-0.80
 149 | 1.18,-1.17
 150 | -0.78,0.66
 151 | -2.09,1.97
 152 | -0.62,0.58
 153 | -1.11,1.23
 154 | 2.56,-2.60
 155 | 0.35,-0.34
 156 | 1.47,-1.41
 157 | 0.14,-0.28
 158 | 0.85,-0.79
 159 | 0.22,-0.31
 160 | -0.03,0.13
 161 | -0.80,0.80
 162 | 0.84,-0.73
 163 | -0.67,0.67
 164 | -1.03,0.85
 165 | 0.95,-0.79
 166 | 0.51,-0.51
 167 | -0.31,0.30
 168 | 0.30,-0.45
 169 | -0.26,0.23
 170 | 1.63,-1.50
 171 | -0.24,0.29
 172 | -0.21,0.11
 173 | 0.64,-0.62
 174 | 1.49,-1.45
 175 | 0.26,-0.34
 176 | -0.51,0.43
 177 | 0.81,-0.72
 178 | -0.80,0.73
 179 | -0.07,0.22
 180 | 1.22,-1.30
 181 | -1.26,1.21
 182 | -0.84,0.83
 183 | 1.91,-1.83
 184 | 0.10,-0.18
 185 | -0.91,1.03
 186 | 0.74,-0.58
 187 | 0.12,-0.23
 188 | 0.39,-0.46
 189 | -1.09,1.06
 190 | -1.58,1.65
 191 | -0.22,0.40
 192 | -3.74,3.75
 193 | 0.16,-0.21
 194 | 0.40,-0.45
 195 | 1.72,-1.89
 196 | -0.91,0.91
 197 | -0.35,0.47
 198 | 0.90,-0.93
 199 | 0.93,-0.85
 200 | 0.15,-0.20
 201 | 0.01,-0.06
 202 | 0.15,-0.26
 203 | 0.73,-0.78
 204 | -0.89,1.04
 205 | -0.76,0.66
 206 | 1.07,-1.06
 207 | 0.29,-0.25
 208 | 0.17,-0.10
 209 | -0.70,0.75
 210 | 0.29,-0.25
 211 | 1.50,-1.60
 212 | 0.98,-0.91
 213 | -0.02,-0.11
 214 | 0.78,-0.79
 215 | -1.09,1.18
 216 | 0.14,-0.11
 217 | -0.53,0.31
 218 | 0.21,-0.25
 219 | -0.45,0.32
 220 | 0.83,-0.81
 221 | 0.11,-0.16
 222 | -0.24,0.26
 223 | -0.36,0.41
 224 | -1.20,1.20
 225 | 0.66,-0.66
 226 | -0.01,0.21
 227 | 0.29,-0.21
 228 | -0.95,1.08
 229 | -0.28,0.42
 230 | -0.16,0.22
 231 | -1.88,1.89
 232 | -1.36,1.41
 233 | 0.71,-0.85
 234 | 0.09,-0.16
 235 | 1.26,-1.35
 236 | -0.60,0.61
 237 | -0.95,0.81
 238 | -0.68,0.88
 239 | 0.97,-0.85
 240 | 1.06,-1.05
 241 | 1.62,-1.80
 242 | 1.63,-1.62
 243 | 1.59,-1.77
 244 | 0.16,-0.06
 245 | -0.01,-0.04
 246 | 0.54,-0.42
 247 | -0.81,0.89
 248 | 2.25,-2.24
 249 | -0.88,0.77
 250 | 0.64,-0.70
 251 | 0.33,-0.25
 252 | -0.65,0.64
 253 | -0.75,0.72
 254 | -1.17,1.24
 255 | -0.30,0.31
 256 | 1.52,-1.51
 257 | 0.07,0.09
 258 | 1.66,-1.67
 259 | 0.04,0.01
 260 | -0.33,0.30
 261 | 0.46,-0.43
 262 | 0.59,-0.69
 263 | 1.18,-1.29
 264 | 0.97,-0.89
 265 | 1.05,-1.15
 266 | 1.64,-1.41
 267 | 0.43,-0.47
 268 | 0.58,-0.66
 269 | -2.58,2.57
 270 | 0.15,-0.35
 271 | 0.23,-0.31
 272 | 0.21,-0.18
 273 | -0.39,0.27
 274 | 0.53,-0.47
 275 | -0.10,0.07
 276 | -1.53,1.68
 277 | 0.30,-0.36
 278 | -0.04,-0.13
 279 | -1.24,1.09
 280 | 1.51,-1.57
 281 | 0.95,-1.01
 282 | 0.40,-0.39
 283 | 0.23,-0.24
 284 | 0.25,-0.18
 285 | 1.27,-1.17
 286 | 1.11,-1.20
 287 | 0.79,-0.72
 288 | 1.14,-1.21
 289 | 0.79,-0.68
 290 | -0.82,0.70
 291 | 0.66,-0.71
 292 | -0.08,0.14
 293 | 1.54,-1.52
 294 | -0.71,0.55
 295 | -0.42,0.45
 296 | 0.08,-0.06
 297 | 1.42,-1.31
 298 | -0.05,-0.02
 299 | 1.83,-1.70
 300 | 0.24,-0.15
 301 | 0.65,-0.45
 302 | 0.20,-0.26
 303 | -0.97,0.96
 304 | 0.90,-0.87
 305 | 0.29,-0.16
 306 | 1.32,-1.53
 307 | -0.11,0.11
 308 | 1.03,-0.90
 309 | -0.51,0.69
 310 | 1.14,-1.09
 311 | 1.64,-1.50
 312 | -0.53,0.62
 313 | 2.48,-2.53
 314 | -1.04,1.17
 315 | 1.10,-0.99
 316 | -1.60,1.63
 317 | -1.07,1.03
 318 | 0.49,-0.44
 319 | -0.43,0.39
 320 | 0.46,-0.44
 321 | -0.65,0.65
 322 | -0.09,0.17
 323 | 0.87,-0.88
 324 | 0.34,-0.40
 325 | 0.97,-0.90
 326 | 0.25,-0.21
 327 | 1.96,-1.95
 328 | 0.70,-0.53
 329 | -1.46,1.41
 330 | -1.57,1.56
 331 | -0.98,1.03
 332 | 1.44,-1.42
 333 | 1.03,-0.97
 334 | -0.05,-0.06
 335 | 0.80,-0.90
 336 | -0.34,0.25
 337 | 0.69,-0.63
 338 | -1.67,1.46
 339 | 0.70,-0.55
 340 | 0.50,-0.62
 341 | -1.08,1.12
 342 | 0.37,-0.36
 343 | -0.87,0.87
 344 | 1.12,-1.10
 345 | -0.92,0.95
 346 | 0.26,-0.26
 347 | 0.49,-0.64
 348 | 1.48,-1.49
 349 | -0.02,-0.08
 350 | 1.11,-1.29
 351 | -1.66,1.64
 352 | 0.97,-0.92
 353 | -0.09,0.10
 354 | 0.09,0.01
 355 | -0.62,0.68
 356 | -1.75,1.69
 357 | 0.58,-0.57
 358 | 0.86,-0.89
 359 | 1.93,-2.09
 360 | 2.31,-2.30
 361 | 0.16,-0.20
 362 | 0.75,-0.60
 363 | -0.59,0.39
 364 | -0.52,0.53
 365 | 0.09,-0.11
 366 | 0.72,-0.91
 367 | -0.68,0.80
 368 | 1.00,-0.97
 369 | -0.60,0.56
 370 | 0.84,-0.82
 371 | 0.25,-0.24
 372 | 1.80,-1.79
 373 | 0.08,0.01
 374 | -0.00,0.03
 375 | -0.49,0.44
 376 | 0.65,-0.54
 377 | -0.46,0.64
 378 | -0.29,0.34
 379 | 0.42,-0.29
 380 | -0.53,0.51
 381 | 0.17,-0.38
 382 | -0.95,0.84
 383 | 2.09,-2.14
 384 | -2.36,2.63
 385 | -0.21,0.36
 386 | -2.54,2.39
 387 | -0.16,0.16
 388 | 0.30,-0.29
 389 | -0.10,0.11
 390 | 0.93,-0.96
 391 | -1.17,1.25
 392 | 0.02,-0.03
 393 | -0.25,0.28
 394 | -0.97,0.91
 395 | -0.35,0.33
 396 | -0.71,0.88
 397 | 0.25,-0.09
 398 | 0.00,-0.06
 399 | -0.07,0.06
 400 | -0.49,0.65
 401 | -2.27,2.19
 402 | 0.54,-0.72
 403 | 0.09,-0.02
 404 | -0.02,-0.04
 405 | 0.13,-0.11
 406 | -0.33,0.29
 407 | -1.34,1.30
 408 | -1.14,1.15
 409 | 0.68,-0.64
 410 | -0.78,0.81
 411 | 0.90,-0.83
 412 | -0.19,0.44
 413 | -0.01,0.19
 414 | 0.49,-0.37
 415 | 0.02,0.01
 416 | -0.69,0.74
 417 | -1.20,1.11
 418 | -0.09,0.16
 419 | -0.54,0.52
 420 | 1.01,-0.97
 421 | 0.24,-0.27
 422 | 0.55,-0.55
 423 | 0.36,-0.47
 424 | 1.39,-1.38
 425 | 0.63,-0.56
 426 | 0.94,-0.88
 427 | -1.27,1.19
 428 | 0.58,-0.61
 429 | 0.41,-0.41
 430 | 1.08,-1.08
 431 | 0.42,-0.41
 432 | -0.61,0.59
 433 | -1.33,1.48
 434 | 0.07,-0.07
 435 | -0.05,0.18
 436 | -0.25,0.22
 437 | 0.77,-0.68
 438 | 0.11,0.05
 439 | -1.23,1.19
 440 | -0.28,0.29
 441 | -1.87,1.98
 442 | 1.50,-1.61
 443 | 0.54,-0.51
 444 | -0.63,0.61
 445 | -0.23,0.24
 446 | -0.16,0.32
 447 | -0.55,0.64
 448 | -0.89,0.88
 449 | -0.22,0.29
 450 | 0.53,-0.49
 451 | -0.18,0.14
 452 | 1.73,-1.63
 453 | 0.67,-0.73
 454 | 0.42,-0.43
 455 | 0.43,-0.42
 456 | -0.57,0.54
 457 | -0.32,0.21
 458 | 1.41,-1.21
 459 | -0.17,0.19
 460 | -0.02,-0.04
 461 | -1.64,1.84
 462 | 0.34,-0.40
 463 | 0.82,-0.83
 464 | -0.10,0.01
 465 | -1.47,1.46
 466 | -1.25,1.32
 467 | -0.26,0.11
 468 | 0.89,-0.63
 469 | -0.10,0.05
 470 | 0.26,-0.20
 471 | -1.80,1.84
 472 | 0.96,-1.08
 473 | 0.45,-0.42
 474 | 0.39,-0.29
 475 | 1.37,-1.41
 476 | -1.94,1.94
 477 | 2.14,-2.19
 478 | 0.45,-0.41
 479 | -0.84,0.89
 480 | -0.30,0.35
 481 | -1.03,1.07
 482 | 1.76,-1.87
 483 | 1.16,-1.22
 484 | -0.48,0.55
 485 | -1.29,1.14
 486 | -0.16,0.14
 487 | 0.23,-0.30
 488 | 0.05,-0.02
 489 | -0.10,0.13
 490 | -0.19,0.29
 491 | 1.54,-1.53
 492 | 0.28,-0.35
 493 | 0.59,-0.60
 494 | -1.37,1.25
 495 | -0.80,0.80
 496 | -1.10,1.08
 497 | 0.96,-0.84
 498 | 0.50,-0.48
 499 | -0.24,0.24
 500 | -0.94,1.02
 501 | -0.51,0.34
 502 | 0.33,-0.17
 503 | -0.10,0.26
 504 | -1.63,1.58
 505 | -0.72,0.84
 506 | -0.42,0.36
 507 | 0.37,-0.47
 508 | -1.58,1.65
 509 | -0.32,0.25
 510 | -1.50,1.38
 511 | -0.14,0.22
 512 | -1.83,1.68
 513 | -2.60,2.58
 514 | -0.10,0.10
 515 | 0.98,-0.99
 516 | -0.31,0.26
 517 | -0.98,1.18
 518 | 0.13,-0.15
 519 | -1.35,1.24
 520 | -0.61,0.63
 521 | 0.06,-0.14
 522 | 0.90,-0.72
 523 | -1.54,1.75
 524 | -0.72,0.67
 525 | 0.48,-0.58
 526 | 0.50,-0.65
 527 | -0.21,0.33
 528 | -1.57,1.43
 529 | -1.37,1.35
 530 | -0.35,0.42
 531 | -0.20,0.30
 532 | -1.08,1.10
 533 | 0.64,-0.48
 534 | -1.80,1.80
 535 | -1.60,1.54
 536 | -0.38,0.17
 537 | -0.30,0.16
 538 | -0.15,0.18
 539 | 0.95,-0.89
 540 | 0.45,-0.63
 541 | -1.68,1.57
 542 | -0.55,0.69
 543 | 0.17,-0.02
 544 | 1.52,-1.52
 545 | 2.08,-2.22
 546 | 1.31,-1.33
 547 | 0.38,-0.26
 548 | -0.01,0.09
 549 | -1.66,1.71
 550 | -0.30,0.18
 551 | -0.96,0.98
 552 | -0.93,0.80
 553 | -0.79,0.82
 554 | 1.00,-1.04
 555 | -1.02,0.96
 556 | -0.35,0.40
 557 | 0.78,-0.81
 558 | -0.92,1.02
 559 | -3.23,3.26
 560 | 0.34,-0.27
 561 | 0.45,-0.65
 562 | 0.14,-0.31
 563 | -1.68,1.71
 564 | -0.81,0.73
 565 | -0.05,0.01
 566 | -1.14,0.91
 567 | 1.86,-1.87
 568 | -0.40,0.46
 569 | -0.26,0.54
 570 | -1.59,1.59
 571 | 0.86,-1.08
 572 | 0.72,-0.78
 573 | 0.49,-0.52
 574 | 0.89,-0.98
 575 | -1.20,1.36
 576 | 0.02,0.00
 577 | 0.32,-0.38
 578 | -0.88,0.73
 579 | -0.00,-0.10
 580 | -1.98,2.10
 581 | -1.25,1.23
 582 | 2.27,-2.32
 583 | 1.14,-1.06
 584 | 0.26,-0.29
 585 | -0.98,1.04
 586 | 0.53,-0.28
 587 | -1.00,0.87
 588 | 0.56,-0.58
 589 | -1.01,1.17
 590 | 0.69,-0.60
 591 | 1.02,-1.05
 592 | 0.61,-0.75
 593 | 0.51,-0.31
 594 | 0.10,-0.12
 595 | 0.53,-0.44
 596 | -1.50,1.40
 597 | 1.59,-1.58
 598 | -0.48,0.69
 599 | -0.40,0.56
 600 | -0.36,0.48
 601 | -0.97,0.79
 602 | -1.40,1.46
 603 | 1.86,-1.87
 604 | 1.09,-1.05
 605 | -0.73,0.67
 606 | 1.13,-1.34
 607 | 1.04,-0.89
 608 | -0.02,-0.11
 609 | 0.15,-0.27
 610 | -0.75,0.65
 611 | 1.47,-1.29
 612 | -1.15,1.29
 613 | -0.25,0.39
 614 | 1.04,-1.05
 615 | -2.89,2.89
 616 | 0.55,-0.44
 617 | 0.55,-0.33
 618 | 0.95,-0.95
 619 | -0.61,0.74
 620 | -0.15,0.23
 621 | -0.93,0.91
 622 | -0.54,0.63
 623 | -0.78,0.95
 624 | -0.41,0.41
 625 | -1.35,1.19
 626 | 1.82,-1.71
 627 | 0.25,-0.19
 628 | -1.08,1.18
 629 | -0.31,0.21
 630 | -0.92,1.00
 631 | 0.95,-1.05
 632 | 2.00,-1.85
 633 | -1.70,1.79
 634 | -0.60,0.53
 635 | 0.74,-0.60
 636 | -0.18,0.09
 637 | -0.20,0.33
 638 | 0.65,-0.60
 639 | -2.14,2.09
 640 | -1.35,1.43
 641 | -1.01,0.84
 642 | 1.10,-0.95
 643 | -0.31,0.25
 644 | 1.13,-1.25
 645 | -1.03,0.88
 646 | 1.25,-1.33
 647 | -0.19,0.21
 648 | -0.90,0.89
 649 | 1.01,-0.94
 650 | -1.34,1.33
 651 | -1.23,1.09
 652 | 1.50,-1.56
 653 | 0.44,-0.38
 654 | -1.01,1.08
 655 | 0.69,-0.62
 656 | 0.78,-0.78
 657 | -0.21,0.14
 658 | 0.11,-0.14
 659 | 0.99,-0.88
 660 | -0.91,1.02
 661 | 2.67,-2.51
 662 | -1.40,1.30
 663 | -0.11,0.27
 664 | 0.38,-0.33
 665 | 0.49,-0.45
 666 | -0.18,-0.01
 667 | 0.77,-0.74
 668 | 2.62,-2.69
 669 | -0.54,0.40
 670 | -0.56,0.78
 671 | -1.97,1.85
 672 | 0.31,-0.31
 673 | 0.08,-0.08
 674 | -0.37,0.61
 675 | -0.41,0.32
 676 | 1.65,-1.57
 677 | 1.54,-1.72
 678 | -0.09,0.01
 679 | -0.80,0.80
 680 | -0.70,0.55
 681 | -1.41,1.23
 682 | 0.03,0.02
 683 | 0.25,-0.24
 684 | -0.85,0.85
 685 | -0.04,0.23
 686 | 0.05,-0.16
 687 | -0.54,0.49
 688 | -0.60,0.35
 689 | -0.91,0.71
 690 | -0.34,0.32
 691 | 0.41,-0.44
 692 | -1.38,1.23
 693 | 0.89,-0.83
 694 | -0.19,0.16
 695 | 0.06,-0.18
 696 | 1.74,-1.56
 697 | 0.36,-0.43
 698 | -2.22,2.15
 699 | 0.93,-0.93
 700 | 0.86,-0.96
 701 | -0.70,0.76
 702 | -0.99,1.08
 703 | -0.47,0.47
 704 | -0.72,0.59
 705 | -0.18,0.31
 706 | 1.34,-1.31
 707 | 0.12,0.01
 708 | 1.20,-1.20
 709 | 0.78,-0.69
 710 | 1.38,-1.33
 711 | -0.06,-0.02
 712 | 1.95,-2.10
 713 | -0.42,0.46
 714 | -0.11,0.04
 715 | 0.70,-0.82
 716 | 1.05,-1.01
 717 | -1.09,1.04
 718 | 1.36,-1.46
 719 | 0.10,0.20
 720 | -1.18,1.23
 721 | -1.91,1.95
 722 | 0.68,-0.84
 723 | -2.36,2.43
 724 | 1.31,-1.28
 725 | -0.97,1.04
 726 | 0.18,-0.07
 727 | -0.77,0.94
 728 | 0.68,-0.63
 729 | -0.85,0.83
 730 | 1.93,-1.71
 731 | -0.91,0.86
 732 | 1.53,-1.75
 733 | -0.79,0.91
 734 | 1.56,-1.62
 735 | -0.00,-0.06
 736 | 1.01,-0.90
 737 | 1.16,-1.15
 738 | 0.73,-0.70
 739 | 1.05,-0.88
 740 | 1.54,-1.60
 741 | 0.05,-0.06
 742 | -1.16,1.12
 743 | -0.62,0.59
 744 | 0.63,-0.70
 745 | 0.11,-0.01
 746 | -0.42,0.49
 747 | 0.34,-0.20
 748 | 0.16,-0.31
 749 | -0.11,0.15
 750 | 0.97,-0.84
 751 | 0.03,-0.10
 752 | 1.19,-1.19
 753 | 0.30,-0.21
 754 | -0.05,0.02
 755 | -0.39,0.22
 756 | 1.05,-1.08
 757 | -1.45,1.52
 758 | -0.25,0.29
 759 | 1.98,-2.06
 760 | 0.82,-0.73
 761 | -0.71,0.62
 762 | -0.13,0.16
 763 | -0.73,0.54
 764 | -0.95,0.96
 765 | 0.42,-0.46
 766 | 1.76,-1.73
 767 | -1.30,1.11
 768 | 0.40,-0.51
 769 | 1.85,-1.81
 770 | 0.73,-0.68
 771 | -1.68,1.75
 772 | 0.61,-0.56
 773 | 1.80,-1.69
 774 | -1.20,1.31
 775 | -0.55,0.48
 776 | -1.27,1.20
 777 | -1.24,1.17
 778 | 0.24,-0.22
 779 | 0.60,-0.69
 780 | 0.91,-0.95
 781 | -0.30,0.40
 782 | -0.44,0.43
 783 | 0.03,0.03
 784 | 1.44,-1.27
 785 | 0.55,-0.48
 786 | -0.33,0.25
 787 | -0.18,0.10
 788 | 1.08,-1.11
 789 | -1.17,1.12
 790 | -1.36,1.37
 791 | 1.82,-1.76
 792 | -0.40,0.37
 793 | -0.44,0.45
 794 | 0.29,-0.23
 795 | 0.13,-0.07
 796 | -1.84,1.90
 797 | 0.10,-0.22
 798 | -0.62,0.60
 799 | 0.95,-1.04
 800 | 0.75,-0.85
 801 | -0.28,0.33
 802 | -0.05,-0.11
 803 | -1.39,1.44
 804 | -0.39,0.45
 805 | 1.82,-1.84
 806 | -1.66,1.61
 807 | 0.29,-0.27
 808 | 0.34,-0.52
 809 | -0.13,0.04
 810 | -0.07,0.07
 811 | -0.41,0.27
 812 | -1.00,1.00
 813 | 0.32,-0.20
 814 | 0.90,-0.90
 815 | -0.20,0.06
 816 | -0.75,0.80
 817 | 0.85,-0.74
 818 | -0.34,0.39
 819 | 0.30,-0.26
 820 | -0.28,0.36
 821 | 0.31,-0.31
 822 | 0.45,-0.52
 823 | 1.17,-1.21
 824 | -0.11,0.12
 825 | 0.67,-0.80
 826 | -0.90,0.78
 827 | 0.01,-0.15
 828 | -0.21,0.32
 829 | 1.40,-1.59
 830 | 0.74,-0.78
 831 | 1.27,-1.20
 832 | -0.40,0.30
 833 | -0.59,0.54
 834 | -0.81,0.86
 835 | -0.30,0.16
 836 | -0.20,0.28
 837 | 0.56,-0.39
 838 | 0.15,-0.26
 839 | -0.93,1.06
 840 | 0.90,-0.92
 841 | 1.17,-1.40
 842 | 0.84,-0.59
 843 | 2.71,-2.90
 844 | -0.19,0.16
 845 | 0.93,-0.96
 846 | -0.02,-0.12
 847 | -0.88,0.81
 848 | 0.45,-0.47
 849 | 1.29,-1.43
 850 | 1.16,-1.05
 851 | 1.55,-1.60
 852 | 0.27,-0.33
 853 | 0.48,-0.58
 854 | 1.19,-1.12
 855 | 1.09,-1.11
 856 | 0.38,-0.39
 857 | -0.64,0.62
 858 | 1.74,-1.52
 859 | 0.98,-1.15
 860 | -0.30,0.41
 861 | 0.35,-0.50
 862 | -0.59,0.60
 863 | -0.69,0.57
 864 | -1.36,1.25
 865 | -0.56,0.64
 866 | 0.18,-0.21
 867 | -0.16,0.02
 868 | 0.63,-0.65
 869 | -0.74,0.68
 870 | -0.44,0.50
 871 | 0.68,-0.74
 872 | 1.69,-1.66
 873 | -1.66,1.77
 874 | 0.21,-0.18
 875 | 0.22,-0.32
 876 | -0.14,0.29
 877 | -0.63,0.55
 878 | -0.81,0.83
 879 | -0.37,0.37
 880 | -1.54,1.61
 881 | -0.29,0.41
 882 | 1.78,-1.77
 883 | -1.10,1.07
 884 | -0.73,0.63
 885 | 0.35,-0.13
 886 | -0.05,0.09
 887 | -0.07,0.02
 888 | 2.76,-2.80
 889 | -0.37,0.44
 890 | 0.14,-0.08
 891 | -0.12,-0.03
 892 | 0.24,-0.30
 893 | -1.42,1.48
 894 | 0.90,-0.96
 895 | -1.25,1.20
 896 | -2.54,2.49
 897 | -0.48,0.57
 898 | 0.96,-1.05
 899 | -3.54,3.44
 900 | -0.02,0.14
 901 | -0.24,0.06
 902 | -2.45,2.44
 903 | 1.61,-1.64
 904 | 1.45,-1.50
 905 | -0.71,0.68
 906 | 1.13,-1.08
 907 | 0.45,-0.31
 908 | -0.25,0.26
 909 | -0.52,0.56
 910 | -0.32,0.36
 911 | -0.82,1.04
 912 | 0.67,-0.64
 913 | 0.78,-0.80
 914 | 1.35,-1.35
 915 | 0.99,-1.00
 916 | -0.30,0.28
 917 | -0.14,0.38
 918 | 0.10,-0.07
 919 | -0.57,0.42
 920 | 0.45,-0.56
 921 | 1.53,-1.45
 922 | 0.41,-0.55
 923 | 0.22,-0.38
 924 | 1.26,-1.31
 925 | 0.65,-0.64
 926 | 1.28,-1.20
 927 | -0.73,0.74
 928 | 0.11,-0.04
 929 | -1.82,1.85
 930 | -0.40,0.22
 931 | 0.55,-0.66
 932 | -1.16,0.97
 933 | -0.19,0.12
 934 | -2.06,1.95
 935 | -0.75,0.84
 936 | 0.68,-0.61
 937 | 0.24,-0.28
 938 | -0.69,0.73
 939 | 1.00,-1.08
 940 | -0.58,0.77
 941 | -0.48,0.34
 942 | -0.81,0.95
 943 | -0.76,0.87
 944 | -0.34,0.32
 945 | 1.06,-1.11
 946 | 0.95,-0.86
 947 | 1.41,-1.47
 948 | 0.19,-0.22
 949 | 0.58,-0.51
 950 | 0.19,-0.09
 951 | 0.26,-0.31
 952 | 0.69,-0.81
 953 | 1.53,-1.58
 954 | 0.69,-0.73
 955 | 0.19,-0.20
 956 | -0.79,0.95
 957 | 0.42,-0.36
 958 | 0.69,-0.87
 959 | 0.87,-1.02
 960 | 0.73,-0.80
 961 | 0.47,-0.34
 962 | 0.40,-0.46
 963 | -0.63,0.49
 964 | -0.70,0.77
 965 | -1.54,1.49
 966 | 1.78,-1.94
 967 | 0.21,-0.36
 968 | 0.38,-0.46
 969 | 1.53,-1.54
 970 | 0.98,-1.06
 971 | -0.17,0.07
 972 | -0.89,0.91
 973 | -0.96,0.89
 974 | 0.05,0.00
 975 | 0.09,-0.14
 976 | -1.69,1.60
 977 | -1.30,1.37
 978 | 2.09,-2.08
 979 | -0.10,0.02
 980 | 1.50,-1.24
 981 | -0.65,0.73
 982 | -0.98,0.90
 983 | -0.35,0.25
 984 | -0.71,0.72
 985 | 0.88,-0.80
 986 | -2.00,2.02
 987 | -1.43,1.38
 988 | 0.81,-0.81
 989 | -0.75,0.78
 990 | 0.18,-0.39
 991 | 0.08,-0.19
 992 | -0.12,0.27
 993 | 0.38,-0.52
 994 | -2.43,2.34
 995 | -0.02,-0.01
 996 | 0.00,-0.14
 997 | -0.78,0.94
 998 | 0.51,-0.38
 999 | -0.28,0.27
1000 | -0.56,0.41
1001 | 


--------------------------------------------------------------------------------
/spark-linear-regression.py:
--------------------------------------------------------------------------------
 1 | from __future__ import print_function
 2 | 
 3 | from pyspark.ml.regression import LinearRegression
 4 | 
 5 | from pyspark.sql import SparkSession
 6 | from pyspark.ml.linalg import Vectors
 7 | 
 8 | if __name__ == "__main__":
 9 | 
10 |     # Create a SparkSession (Note, the config section is only for Windows!)
11 |     spark = SparkSession.builder.config("spark.sql.warehouse.dir", "file:///C:/temp").appName("LinearRegression").getOrCreate()
12 | 
13 |     # Load up our data and convert it to the format MLLib expects.
14 |     inputLines = spark.sparkContext.textFile("regression.txt")
15 |     data = inputLines.map(lambda x: x.split(",")).map(lambda x: (float(x[0]), Vectors.dense(float(x[1]))))
16 | 
17 |     # Convert this RDD to a DataFrame
18 |     colNames = ["label", "features"]
19 |     df = data.toDF(colNames)
20 | 
21 |     # Note, there are lots of cases where you can avoid going from an RDD to a DataFrame.
22 |     # Perhaps you're importing data from a real database. Or you are using structured streaming
23 |     # to get your data.
24 | 
25 |     # Let's split our data into training data and testing data
26 |     trainTest = df.randomSplit([0.5, 0.5])
27 |     trainingDF = trainTest[0]
28 |     testDF = trainTest[1]
29 | 
30 |     # Now create our linear regression model
31 |     lir = LinearRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
32 | 
33 |     # Train the model using our training data
34 |     model = lir.fit(trainingDF)
35 | 
36 |     # Now see if we can predict values in our test data.
37 |     # Generate predictions using our linear regression model for all features in our
38 |     # test dataframe:
39 |     fullPredictions = model.transform(testDF).cache()
40 | 
41 |     # Extract the predictions and the "known" correct labels.
42 |     predictions = fullPredictions.select("prediction").rdd.map(lambda x: x[0])
43 |     labels = fullPredictions.select("label").rdd.map(lambda x: x[0])
44 | 
45 |     # Zip them together
46 |     predictionAndLabel = predictions.zip(labels).collect()
47 | 
48 |     # Print out the predicted and actual values for each point
49 |     for prediction in predictionAndLabel:
50 |       print(prediction)
51 | 
52 | 
53 |     # Stop the session
54 |     spark.stop()
55 | 


--------------------------------------------------------------------------------
/spark-sql.py:
--------------------------------------------------------------------------------
 1 | from pyspark.sql import SparkSession
 2 | from pyspark.sql import Row
 3 | 
 4 | import collections
 5 | 
 6 | # Create a SparkSession (Note, the config section is only for Windows!)
 7 | spark = SparkSession.builder.config("spark.sql.warehouse.dir", "file:///C:/temp").appName("SparkSQL").getOrCreate()
 8 | 
 9 | def mapper(line):
10 |     fields = line.split(',')
11 |     return Row(ID=int(fields[0]), name=str(fields[1].encode("utf-8")), age=int(fields[2]), numFriends=int(fields[3]))
12 | 
13 | lines = spark.sparkContext.textFile("fakefriends.csv")
14 | people = lines.map(mapper)
15 | 
16 | # Infer the schema, and register the DataFrame as a table.
17 | schemaPeople = spark.createDataFrame(people).cache()
18 | schemaPeople.createOrReplaceTempView("people")
19 | 
20 | # SQL can be run over DataFrames that have been registered as a table.
21 | teenagers = spark.sql("SELECT * FROM people WHERE age >= 13 AND age <= 19")
22 | 
23 | # The results of SQL queries are RDDs and support all the normal RDD operations.
24 | for teen in teenagers.collect():
25 |   print(teen)
26 | 
27 | # We can also use functions instead of SQL queries:
28 | schemaPeople.groupBy("age").count().orderBy("age").show()
29 | 
30 | spark.stop()
31 | 


--------------------------------------------------------------------------------
/total-spent-by-customer-sorted.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("SpendByCustomerSorted")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | def extractCustomerPricePairs(line):
 7 |     fields = line.split(',')
 8 |     return (int(fields[0]), float(fields[2]))
 9 | 
10 | input = sc.textFile("file:///sparkcourse/customer-orders.csv")
11 | mappedInput = input.map(extractCustomerPricePairs)
12 | totalByCustomer = mappedInput.reduceByKey(lambda x, y: x + y)
13 | 
14 | #Changed for Python 3 compatibility:
15 | #flipped = totalByCustomer.map(lambda (x,y):(y,x))
16 | flipped = totalByCustomer.map(lambda x: (x[1], x[0]))
17 | 
18 | totalByCustomerSorted = flipped.sortByKey()
19 | 
20 | results = totalByCustomerSorted.collect();
21 | for result in results:
22 |     print(result)
23 | 


--------------------------------------------------------------------------------
/total-spent-by-customer.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("SpendByCustomer")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | def extractCustomerPricePairs(line):
 7 |     fields = line.split(',')
 8 |     return (int(fields[0]), float(fields[2]))
 9 | 
10 | input = sc.textFile("file:///sparkcourse/customer-orders.csv")
11 | mappedInput = input.map(extractCustomerPricePairs)
12 | totalByCustomer = mappedInput.reduceByKey(lambda x, y: x + y)
13 | 
14 | results = totalByCustomer.collect();
15 | for result in results:
16 |     print(result)
17 | 


--------------------------------------------------------------------------------
/word-count-better-sorted.py:
--------------------------------------------------------------------------------
 1 | import re
 2 | from pyspark import SparkConf, SparkContext
 3 | 
 4 | def normalizeWords(text):
 5 |     return re.compile(r'\W+', re.UNICODE).split(text.lower())
 6 | 
 7 | conf = SparkConf().setMaster("local").setAppName("WordCount")
 8 | sc = SparkContext(conf = conf)
 9 | 
10 | input = sc.textFile("file:///sparkcourse/book.txt")
11 | words = input.flatMap(normalizeWords)
12 | 
13 | wordCounts = words.map(lambda x: (x, 1)).reduceByKey(lambda x, y: x + y)
14 | wordCountsSorted = wordCounts.map(lambda x: (x[1], x[0])).sortByKey()
15 | results = wordCountsSorted.collect()
16 | 
17 | for result in results:
18 |     count = str(result[0])
19 |     word = result[1].encode('ascii', 'ignore')
20 |     if (word):
21 |         print(word.decode() + ":\t\t" + count)
22 | 


--------------------------------------------------------------------------------
/word-count-better.py:
--------------------------------------------------------------------------------
 1 | import re
 2 | from pyspark import SparkConf, SparkContext
 3 | 
 4 | def normalizeWords(text):
 5 |     return re.compile(r'\W+', re.UNICODE).split(text.lower())
 6 | 
 7 | conf = SparkConf().setMaster("local").setAppName("WordCount")
 8 | sc = SparkContext(conf = conf)
 9 | 
10 | input = sc.textFile("file:///sparkcourse/book.txt")
11 | words = input.flatMap(normalizeWords)
12 | wordCounts = words.countByValue()
13 | 
14 | for word, count in wordCounts.items():
15 |     cleanWord = word.encode('ascii', 'ignore')
16 |     if (cleanWord):
17 |         print(cleanWord.decode() + " " + str(count))
18 | 


--------------------------------------------------------------------------------
/word-count.py:
--------------------------------------------------------------------------------
 1 | from pyspark import SparkConf, SparkContext
 2 | 
 3 | conf = SparkConf().setMaster("local").setAppName("WordCount")
 4 | sc = SparkContext(conf = conf)
 5 | 
 6 | input = sc.textFile("file:///sparkcourse/book.txt")
 7 | words = input.flatMap(lambda x: x.split())
 8 | wordCounts = words.countByValue()
 9 | 
10 | for word, count in wordCounts.items():
11 |     cleanWord = word.encode('ascii', 'ignore')
12 |     if (cleanWord):
13 |         print(cleanWord.decode() + " " + str(count))
14 | 


--------------------------------------------------------------------------------