├── README.md ├── datos ├── RickAndMortyScripts.csv └── top_10_mexico.csv ├── notebooks ├── 2a_pyspark_colab.ipynb ├── 2b_map_reduce.ipynb ├── 2c_k_means.ipynb ├── 3a_funciones_hash.ipynb ├── 3b_indice_inverso.ipynb ├── 3c_minhash.ipynb ├── 3d_busqueda_imagenes.ipynb ├── 3e_lsh.ipynb ├── 3f_hnmslib.ipynb ├── 3g_minhash_pyspark.ipynb ├── 4a_muestreo_presa.ipynb ├── 4b_filtro_bloom.ipynb ├── 4c_elementos_distintos.ipynb ├── 4c_streaming_pyspark.ipynb ├── 4d_momentos.ipynb └── 4e_kafka.ipynb └── slides ├── 1_conceptos_basicos.pdf ├── 2a_almacenamiento_distribuido.pdf ├── 2b_mapeo_reduccion.pdf ├── 2c_algoritmos.pdf ├── 2d_extensiones.pdf ├── 2e_costo_comunicacion.pdf ├── 3a_vecino_mas_cercano.pdf ├── 3b_minhash.pdf ├── 3c_lsh.pdf ├── 4a_flujos_datos.pdf ├── 4b_muestreo_filtrado.pdf ├── 4c_conteo.pdf ├── 4e_momentos.pdf ├── 5a_memoria_externa.pdf ├── 5b_inconsciente_cache.pdf └── 5c_ordenamiento_busqueda.pdf /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/README.md -------------------------------------------------------------------------------- /datos/RickAndMortyScripts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/datos/RickAndMortyScripts.csv -------------------------------------------------------------------------------- /datos/top_10_mexico.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/datos/top_10_mexico.csv -------------------------------------------------------------------------------- /notebooks/2a_pyspark_colab.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/2a_pyspark_colab.ipynb -------------------------------------------------------------------------------- /notebooks/2b_map_reduce.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/2b_map_reduce.ipynb -------------------------------------------------------------------------------- /notebooks/2c_k_means.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/2c_k_means.ipynb -------------------------------------------------------------------------------- /notebooks/3a_funciones_hash.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3a_funciones_hash.ipynb -------------------------------------------------------------------------------- /notebooks/3b_indice_inverso.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3b_indice_inverso.ipynb -------------------------------------------------------------------------------- /notebooks/3c_minhash.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3c_minhash.ipynb -------------------------------------------------------------------------------- /notebooks/3d_busqueda_imagenes.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3d_busqueda_imagenes.ipynb -------------------------------------------------------------------------------- /notebooks/3e_lsh.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3e_lsh.ipynb -------------------------------------------------------------------------------- /notebooks/3f_hnmslib.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3f_hnmslib.ipynb -------------------------------------------------------------------------------- /notebooks/3g_minhash_pyspark.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/3g_minhash_pyspark.ipynb -------------------------------------------------------------------------------- /notebooks/4a_muestreo_presa.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/4a_muestreo_presa.ipynb -------------------------------------------------------------------------------- /notebooks/4b_filtro_bloom.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/4b_filtro_bloom.ipynb -------------------------------------------------------------------------------- /notebooks/4c_elementos_distintos.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/4c_elementos_distintos.ipynb -------------------------------------------------------------------------------- /notebooks/4c_streaming_pyspark.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/4c_streaming_pyspark.ipynb -------------------------------------------------------------------------------- /notebooks/4d_momentos.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/4d_momentos.ipynb -------------------------------------------------------------------------------- /notebooks/4e_kafka.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/notebooks/4e_kafka.ipynb -------------------------------------------------------------------------------- /slides/1_conceptos_basicos.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/1_conceptos_basicos.pdf -------------------------------------------------------------------------------- /slides/2a_almacenamiento_distribuido.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/2a_almacenamiento_distribuido.pdf -------------------------------------------------------------------------------- /slides/2b_mapeo_reduccion.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/2b_mapeo_reduccion.pdf -------------------------------------------------------------------------------- /slides/2c_algoritmos.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/2c_algoritmos.pdf -------------------------------------------------------------------------------- /slides/2d_extensiones.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/2d_extensiones.pdf -------------------------------------------------------------------------------- /slides/2e_costo_comunicacion.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/2e_costo_comunicacion.pdf -------------------------------------------------------------------------------- /slides/3a_vecino_mas_cercano.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/3a_vecino_mas_cercano.pdf -------------------------------------------------------------------------------- /slides/3b_minhash.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/3b_minhash.pdf -------------------------------------------------------------------------------- /slides/3c_lsh.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/3c_lsh.pdf -------------------------------------------------------------------------------- /slides/4a_flujos_datos.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/4a_flujos_datos.pdf -------------------------------------------------------------------------------- /slides/4b_muestreo_filtrado.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/4b_muestreo_filtrado.pdf -------------------------------------------------------------------------------- /slides/4c_conteo.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/4c_conteo.pdf -------------------------------------------------------------------------------- /slides/4e_momentos.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/4e_momentos.pdf -------------------------------------------------------------------------------- /slides/5a_memoria_externa.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/5a_memoria_externa.pdf -------------------------------------------------------------------------------- /slides/5b_inconsciente_cache.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/5b_inconsciente_cache.pdf -------------------------------------------------------------------------------- /slides/5c_ordenamiento_busqueda.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gibranfp/CursoDatosMasivosI/HEAD/slides/5c_ordenamiento_busqueda.pdf --------------------------------------------------------------------------------