├── 2017 └── 10 │ └── 01 │ └── snake.html ├── 2018 └── 11 │ └── MostCommonWordsSpanish.ipynb ├── 2020 └── 05 │ └── 03 │ └── index.html └── README.md /README.md: -------------------------------------------------------------------------------- 1 | # src 2 | Sources for some videos 3 | -------------------------------------------------------------------------------- /2020/05/03/index.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 69 | -------------------------------------------------------------------------------- /2017/10/01/snake.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 117 | -------------------------------------------------------------------------------- /2018/11/MostCommonWordsSpanish.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "metadata": {}, 7 | "outputs": [ 8 | { 9 | "name": "stdout", 10 | "output_type": "stream", 11 | "text": [ 12 | "120-million-word-spanish-corpus.zip Untitled.ipynb\r\n" 13 | ] 14 | } 15 | ], 16 | "source": [ 17 | "!ls\n" 18 | ] 19 | }, 20 | { 21 | "cell_type": "code", 22 | "execution_count": 2, 23 | "metadata": {}, 24 | "outputs": [ 25 | { 26 | "name": "stdout", 27 | "output_type": "stream", 28 | "text": [ 29 | "Archive: 120-million-word-spanish-corpus.zip\n", 30 | " inflating: spanish_corpus/spanishText_10000_15000 \n", 31 | " inflating: spanish_corpus/spanishText_110000_115000 \n", 32 | " inflating: spanish_corpus/spanishText_120000_125000 \n", 33 | " inflating: spanish_corpus/spanishText_15000_20000 \n", 34 | " inflating: spanish_corpus/spanishText_180000_185000 \n", 35 | " inflating: spanish_corpus/spanishText_185000_190000 \n", 36 | " inflating: spanish_corpus/spanishText_200000_205000 \n", 37 | " inflating: spanish_corpus/spanishText_20000_25000 \n", 38 | " inflating: spanish_corpus/spanishText_205000_210000 \n", 39 | " inflating: spanish_corpus/spanishText_210000_215000 \n", 40 | " inflating: spanish_corpus/spanishText_225000_230000 \n", 41 | " inflating: spanish_corpus/spanishText_230000_235000 \n", 42 | " inflating: spanish_corpus/spanishText_25000_30000 \n", 43 | " inflating: spanish_corpus/spanishText_260000_265000 \n", 44 | " inflating: spanish_corpus/spanishText_265000_270000 \n", 45 | " inflating: spanish_corpus/spanishText_270000_275000 \n", 46 | " inflating: spanish_corpus/spanishText_285000_290000 \n", 47 | " inflating: spanish_corpus/spanishText_305000_310000 \n", 48 | " inflating: spanish_corpus/spanishText_310000_315000 \n", 49 | " inflating: spanish_corpus/spanishText_315000_320000 \n", 50 | " inflating: spanish_corpus/spanishText_320000_325000 \n", 51 | " inflating: spanish_corpus/spanishText_325000_330000 \n", 52 | " inflating: spanish_corpus/spanishText_330000_335000 \n", 53 | " inflating: spanish_corpus/spanishText_335000_340000 \n", 54 | " inflating: spanish_corpus/spanishText_340000_345000 \n", 55 | " inflating: spanish_corpus/spanishText_345000_350000 \n", 56 | " inflating: spanish_corpus/spanishText_350000_355000 \n", 57 | " inflating: spanish_corpus/spanishText_355000_360000 \n", 58 | " inflating: spanish_corpus/spanishText_360000_365000 \n", 59 | " inflating: spanish_corpus/spanishText_365000_370000 \n", 60 | " inflating: spanish_corpus/spanishText_370000_375000 \n", 61 | " inflating: spanish_corpus/spanishText_375000_380000 \n", 62 | " inflating: spanish_corpus/spanishText_380000_385000 \n", 63 | " inflating: spanish_corpus/spanishText_385000_390000 \n", 64 | " inflating: spanish_corpus/spanishText_390000_395000 \n", 65 | " inflating: spanish_corpus/spanishText_395000_400000 \n", 66 | " inflating: spanish_corpus/spanishText_400000_405000 \n", 67 | " inflating: spanish_corpus/spanishText_40000_45000 \n", 68 | " inflating: spanish_corpus/spanishText_405000_410000 \n", 69 | " inflating: spanish_corpus/spanishText_410000_415000 \n", 70 | " inflating: spanish_corpus/spanishText_415000_420000 \n", 71 | " inflating: spanish_corpus/spanishText_420000_425000 \n", 72 | " inflating: spanish_corpus/spanishText_425000_430000 \n", 73 | " inflating: spanish_corpus/spanishText_430000_435000 \n", 74 | " inflating: spanish_corpus/spanishText_435000_440000 \n", 75 | " inflating: spanish_corpus/spanishText_440000_445000 \n", 76 | " inflating: spanish_corpus/spanishText_445000_450000 \n", 77 | " inflating: spanish_corpus/spanishText_450000_455000 \n", 78 | " inflating: spanish_corpus/spanishText_45000_50000 \n", 79 | " inflating: spanish_corpus/spanishText_455000_460000 \n", 80 | " inflating: spanish_corpus/spanishText_460000_465000 \n", 81 | " inflating: spanish_corpus/spanishText_465000_470000 \n", 82 | " inflating: spanish_corpus/spanishText_470000_475000 \n", 83 | " inflating: spanish_corpus/spanishText_475000_480000 \n", 84 | " inflating: spanish_corpus/spanishText_480000_485000 \n", 85 | " inflating: spanish_corpus/spanishText_70000_75000 \n", 86 | " inflating: spanish_corpus/spanishText_90000_95000 \n" 87 | ] 88 | } 89 | ], 90 | "source": [ 91 | "!unzip 120-million-word-spanish-corpus.zip" 92 | ] 93 | }, 94 | { 95 | "cell_type": "code", 96 | "execution_count": 8, 97 | "metadata": {}, 98 | "outputs": [ 99 | { 100 | "name": "stdout", 101 | "output_type": "stream", 102 | "text": [ 103 | "\r\n", 104 | "La Laguna de Paca es una laguna que se encuentra muy cerca de la ciudad de Jauja, Per�, lugar preferido de paseo para los jaujinos y muy visitada por gente de todo el Valle del Mantaro.\r\n", 105 | "\r\n", 106 | "Esta laguna se sit�a a 3,418 m.s.n.m. entre los distritos de Paca, Chun�n y Panc�n a 2.5 km al Norte de la ciudad de Jauja. Su espejo de agua es de 21.40 km2 y tiene una capacidad de 85.50 mil m3, los totorales de la laguna sirven de h�bitat a gran variedad de aves silvestres. Es la zona tur�stica m�s visitada del Valle del Mantaro. Su enorme espejo de agua cuenta con hoteles y restaurantes, y durante los fines de semana se llenan de visitantes para pasear por sus aguas o para saborear una deliciosa pachamanca o un plato de trucha frita.\r\n", 107 | "\r\n", 108 | "Hermosa laguna de aguas tranquilas sobre las que se han tejido algunas leyendas. Una de ellas cuenta que en su fondo yacen llamas con cargamentos de oro y plata que fueron lanzadas all� por la caravana de s�bditos del inca que ven�an del Cusco al enterarse que Atahualpa hab�a sido asesinado; el cargamento aparentemente ir�a a incrementar el rescate que este inca ofreci� a los espa�oles por su liberaci�n. Atesora otras leyendas y mitos que se han trasmitido de generaci�n en generaci�n como aqu�l del origen de la laguna, de la sirena de cabellos dorados y de la campana de oro. Se dice tambi�n que esta laguna est� de alguna forma conectada con la Laguna de �ahuimpuquio cerca a la ciudad de Chupaca.\r\n", 109 | "\r\n", 110 | "\r\n", 111 | "\r\n", 112 | "\r\n" 113 | ] 114 | } 115 | ], 116 | "source": [ 117 | "!head spanish_corpus/spanishText_120000_125000" 118 | ] 119 | }, 120 | { 121 | "cell_type": "code", 122 | "execution_count": 9, 123 | "metadata": {}, 124 | "outputs": [ 125 | { 126 | "name": "stdout", 127 | "output_type": "stream", 128 | "text": [ 129 | " 4834\r\n" 130 | ] 131 | } 132 | ], 133 | "source": [ 134 | "!grep 'doc>' spanish_corpus/spanishText_10000_15000 | wc -l" 135 | ] 136 | }, 137 | { 138 | "cell_type": "code", 139 | "execution_count": 12, 140 | "metadata": {}, 141 | "outputs": [], 142 | "source": [] 143 | }, 144 | { 145 | "cell_type": "code", 146 | "execution_count": 45, 147 | "metadata": {}, 148 | "outputs": [], 149 | "source": [ 150 | "def read_lines(f):\n", 151 | " return open(f, encoding='ISO-8859-1').read().splitlines()\n", 152 | "\n", 153 | "def filter_lines(lines):\n", 154 | " for line in lines:\n", 155 | " if line.startswith(']" 1922 | ] 1923 | }, 1924 | "execution_count": 60, 1925 | "metadata": {}, 1926 | "output_type": "execute_result" 1927 | }, 1928 | { 1929 | "data": { 1930 | "image/png": "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\n", 1931 | "text/plain": [ 1932 | "" 1933 | ] 1934 | }, 1935 | "metadata": {}, 1936 | "output_type": "display_data" 1937 | } 1938 | ], 1939 | "source": [ 1940 | "%pylab inline\n", 1941 | "plot([j for i,j in most_common[50:200]])" 1942 | ] 1943 | }, 1944 | { 1945 | "cell_type": "code", 1946 | "execution_count": 96, 1947 | "metadata": {}, 1948 | "outputs": [ 1949 | { 1950 | "data": { 1951 | "text/plain": [ 1952 | "[('de', 7768066),\n", 1953 | " ('la', 4042357),\n", 1954 | " ('en', 3389607),\n", 1955 | " ('el', 3047402),\n", 1956 | " ('y', 2648361),\n", 1957 | " ('a', 1817983),\n", 1958 | " ('que', 1681980),\n", 1959 | " ('los', 1449332),\n", 1960 | " ('del', 1390869),\n", 1961 | " ('se', 1162234),\n", 1962 | " ('un', 976537),\n", 1963 | " ('por', 961098),\n", 1964 | " ('con', 902094),\n", 1965 | " ('las', 884812),\n", 1966 | " ('una', 844113),\n", 1967 | " ('su', 793043),\n", 1968 | " ('es', 731708),\n", 1969 | " ('al', 564421),\n", 1970 | " ('como', 562434),\n", 1971 | " ('para', 551743),\n", 1972 | " ('fue', 403657),\n", 1973 | " ('no', 335792),\n", 1974 | " ('más', 333536),\n", 1975 | " ('o', 299617),\n", 1976 | " ('sus', 270337),\n", 1977 | " ('lo', 247800),\n", 1978 | " ('también', 226993),\n", 1979 | " ('entre', 202480),\n", 1980 | " ('este', 177778),\n", 1981 | " ('the', 165971),\n", 1982 | " ('son', 164073),\n", 1983 | " ('esta', 152213),\n", 1984 | " ('pero', 150506),\n", 1985 | " ('años', 150024),\n", 1986 | " ('sobre', 145857),\n", 1987 | " ('le', 145009),\n", 1988 | " ('dos', 144100),\n", 1989 | " ('ha', 137724),\n", 1990 | " ('desde', 137045),\n", 1991 | " ('hasta', 131289),\n", 1992 | " ('ser', 127171),\n", 1993 | " ('enlaces', 126139),\n", 1994 | " ('parte', 123816),\n", 1995 | " ('ciudad', 123539),\n", 1996 | " ('durante', 122820),\n", 1997 | " ('externos', 122385),\n", 1998 | " ('donde', 118051),\n", 1999 | " ('año', 115611),\n", 2000 | " ('sin', 113965),\n", 2001 | " ('era', 112372),\n", 2002 | " ('cuando', 109074),\n", 2003 | " ('of', 107000),\n", 2004 | " ('e', 105607),\n", 2005 | " ('está', 100978),\n", 2006 | " ('gran', 99650),\n", 2007 | " ('san', 99104),\n", 2008 | " ('después', 95679),\n", 2009 | " ('tiene', 92342),\n", 2010 | " ('nombre', 90138),\n", 2011 | " ('ya', 89370),\n", 2012 | " ('otros', 87774),\n", 2013 | " ('puede', 86984),\n", 2014 | " ('historia', 86677),\n", 2015 | " ('primera', 85819),\n", 2016 | " ('muy', 84382),\n", 2017 | " ('uno', 84154),\n", 2018 | " ('primer', 77895),\n", 2019 | " ('así', 77276),\n", 2020 | " ('fueron', 73742),\n", 2021 | " ('forma', 73705),\n", 2022 | " ('siglo', 72556),\n", 2023 | " ('mismo', 71538),\n", 2024 | " ('españa', 69715),\n", 2025 | " ('aunque', 68628),\n", 2026 | " ('todo', 68372),\n", 2027 | " ('nacional', 68263),\n", 2028 | " ('si', 68139),\n", 2029 | " ('referencias', 67686),\n", 2030 | " ('cual', 67658),\n", 2031 | " ('había', 67589),\n", 2032 | " ('tres', 67551),\n", 2033 | " ('guerra', 66864),\n", 2034 | " ('grupo', 66616),\n", 2035 | " ('estado', 66162),\n", 2036 | " ('mayor', 66117),\n", 2037 | " ('población', 65798),\n", 2038 | " ('vez', 64546),\n", 2039 | " ('tras', 62406),\n", 2040 | " ('tiempo', 61678),\n", 2041 | " ('además', 61310),\n", 2042 | " ('general', 60625),\n", 2043 | " ('bajo', 60458),\n", 2044 | " ('lugar', 59693),\n", 2045 | " ('c', 58657),\n", 2046 | " ('cada', 58505),\n", 2047 | " ('sido', 58203),\n", 2048 | " ('todos', 57747),\n", 2049 | " ('%', 56918),\n", 2050 | " ('vida', 56732),\n", 2051 | " ('han', 56722),\n", 2052 | " ('familia', 55902),\n", 2053 | " ('nueva', 55878),\n", 2054 | " ('sur', 55501),\n", 2055 | " ('contra', 55151),\n", 2056 | " ('otras', 54559),\n", 2057 | " ('estados', 54345),\n", 2058 | " ('i', 54267),\n", 2059 | " ('junto', 52690),\n", 2060 | " ('algunos', 52090),\n", 2061 | " ('universidad', 52089),\n", 2062 | " ('hacia', 52031),\n", 2063 | " ('norte', 51886),\n", 2064 | " ('and', 51886),\n", 2065 | " ('m', 51201),\n", 2066 | " ('región', 50869),\n", 2067 | " ('mundo', 50541),\n", 2068 | " ('río', 50205),\n", 2069 | " ('él', 50196),\n", 2070 | " ('partido', 50141),\n", 2071 | " ('inglés', 49965),\n", 2072 | " ('provincia', 49793),\n", 2073 | " ('serie', 49325),\n", 2074 | " ('nuevo', 48850),\n", 2075 | " ('gobierno', 48797),\n", 2076 | " ('encuentra', 48666),\n", 2077 | " ('juan', 48316),\n", 2078 | " ('sólo', 47920),\n", 2079 | " ('ese', 47905),\n", 2080 | " ('embargo', 47749),\n", 2081 | " ('oficial', 47647),\n", 2082 | " ('véase', 47482),\n", 2083 | " ('tanto', 47245),\n", 2084 | " ('antes', 46892),\n", 2085 | " ('hay', 46476),\n", 2086 | " ('estos', 46353),\n", 2087 | " ('s', 45996),\n", 2088 | " ('siendo', 45923),\n", 2089 | " ('mientras', 45604),\n", 2090 | " ('unidos', 45517),\n", 2091 | " ('quien', 45436),\n", 2092 | " ('luego', 45088),\n", 2093 | " ('centro', 44614),\n", 2094 | " ('día', 44590),\n", 2095 | " ('sistema', 44526),\n", 2096 | " ('obra', 44234),\n", 2097 | " ('país', 43246),\n", 2098 | " ('según', 43242),\n", 2099 | " ('josé', 43148),\n", 2100 | " ('otro', 42745),\n", 2101 | " ('\"', 42561),\n", 2102 | " ('segunda', 42317),\n", 2103 | " ('pueden', 42002),\n", 2104 | " ('entonces', 41771),\n", 2105 | " ('equipo', 41626),\n", 2106 | " ('esto', 41403),\n", 2107 | " ('debido', 41206),\n", 2108 | " ('rey', 40733),\n", 2109 | " ('español', 40421),\n", 2110 | " ('iglesia', 40283),\n", 2111 | " ('varios', 40262),\n", 2112 | " ('in', 40254),\n", 2113 | " ('ella', 39962),\n", 2114 | " ('número', 39710),\n", 2115 | " ('zona', 39201),\n", 2116 | " ('banda', 39000),\n", 2117 | " ('final', 38762),\n", 2118 | " ('santa', 38257),\n", 2119 | " ('casa', 38209),\n", 2120 | " ('madrid', 38202),\n", 2121 | " ('julio', 37988),\n", 2122 | " ('muchos', 37579),\n", 2123 | " ('departamento', 37557),\n", 2124 | " ('ellos', 37480),\n", 2125 | " ('méxico', 37372),\n", 2126 | " ('otra', 37175),\n", 2127 | " ('presidente', 37139),\n", 2128 | " ('hace', 37030),\n", 2129 | " ('cuenta', 36998),\n", 2130 | " ('mejor', 36966),\n", 2131 | " ('obras', 36809),\n", 2132 | " ('cuatro', 36719),\n", 2133 | " ('principal', 36486),\n", 2134 | " ('estaba', 36444),\n", 2135 | " ('están', 36435),\n", 2136 | " ('música', 36409),\n", 2137 | " ('dentro', 36367),\n", 2138 | " ('tuvo', 36291),\n", 2139 | " ('grandes', 36118),\n", 2140 | " ('unos', 35738),\n", 2141 | " ('poco', 35460),\n", 2142 | " ('real', 35202),\n", 2143 | " ('película', 35140),\n", 2144 | " ('tipo', 34908),\n", 2145 | " ('álbum', 34848),\n", 2146 | " ('ii', 34836),\n", 2147 | " ('d', 34752),\n", 2148 | " ('poder', 34742),\n", 2149 | " ('bien', 34722),\n", 2150 | " ('argentina', 34517),\n", 2151 | " ('mayo', 34204),\n", 2152 | " ('distrito', 34201),\n", 2153 | " ('muerte', 34148),\n", 2154 | " ('época', 34134),\n", 2155 | " ('club', 33969),\n", 2156 | " ('estas', 33965),\n", 2157 | " ('municipio', 33939),\n", 2158 | " ('medio', 33415),\n", 2159 | " ('eran', 33353),\n", 2160 | " ('especies', 33323),\n", 2161 | " ('algunas', 33272),\n", 2162 | " ('internacional', 32909),\n", 2163 | " ('hijo', 32704),\n", 2164 | " ('les', 32692),\n", 2165 | " ('pueblo', 32687),\n", 2166 | " ('trabajo', 32538),\n", 2167 | " ('personas', 32101),\n", 2168 | " ('segundo', 32088),\n", 2169 | " ('conocido', 31826),\n", 2170 | " ('francia', 31701),\n", 2171 | " ('actualmente', 31677),\n", 2172 | " ('maría', 31667),\n", 2173 | " ('habitantes', 31641),\n", 2174 | " ('solo', 31481),\n", 2175 | " ('mundial', 31378),\n", 2176 | " ('octubre', 31331),\n", 2177 | " ('todas', 30943),\n", 2178 | " ('&', 30825),\n", 2179 | " ('ejemplo', 30796),\n", 2180 | " ('enero', 30676),\n", 2181 | " ('canción', 30658),\n", 2182 | " ('padre', 30638),\n", 2183 | " ('septiembre', 30597),\n", 2184 | " ('largo', 30574),\n", 2185 | " ('tierra', 30453),\n", 2186 | " ('junio', 30448),\n", 2187 | " ('agua', 30447),\n", 2188 | " ('importante', 30343),\n", 2189 | " ('hizo', 30318),\n", 2190 | " ('través', 30251),\n", 2191 | " ('km', 30249),\n", 2192 | " ('agosto', 30019),\n", 2193 | " ('ejército', 30018),\n", 2194 | " ('hecho', 29987),\n", 2195 | " ('carlos', 29930),\n", 2196 | " ('diciembre', 29902),\n", 2197 | " ('menos', 29786),\n", 2198 | " ('isla', 29694),\n", 2199 | " ('misma', 29692),\n", 2200 | " ('temporada', 29607),\n", 2201 | " ('tienen', 29592),\n", 2202 | " ('carrera', 29531),\n", 2203 | " ('llamado', 29484),\n", 2204 | " ('b', 29481),\n", 2205 | " ('varias', 29437),\n", 2206 | " ('capital', 29275),\n", 2207 | " ('toda', 29245),\n", 2208 | " ('marzo', 29177),\n", 2209 | " ('noviembre', 29117),\n", 2210 | " ('abril', 29082),\n", 2211 | " ('http', 28892),\n", 2212 | " ('momento', 28874),\n", 2213 | " ('x', 28835),\n", 2214 | " ('veces', 28713),\n", 2215 | " ('partir', 28623),\n", 2216 | " ('caso', 28572),\n", 2217 | " ('sitio', 28360),\n", 2218 | " ('desarrollo', 28112),\n", 2219 | " ('central', 27835),\n", 2220 | " ('web', 27812),\n", 2221 | " ('tarde', 27697),\n", 2222 | " ('actual', 27474),\n", 2223 | " ('orden', 27471),\n", 2224 | " ('j', 27359),\n", 2225 | " ('punto', 27282),\n", 2226 | " ('política', 27196),\n", 2227 | " ('línea', 27098),\n", 2228 | " ('escuela', 26869),\n", 2229 | " ('mayoría', 26861),\n", 2230 | " ('república', 26858),\n", 2231 | " ('origen', 26772),\n", 2232 | " ('francesa', 26763),\n", 2233 | " ('premio', 26736),\n", 2234 | " ('diferentes', 26699),\n", 2235 | " ('tenía', 26660),\n", 2236 | " ('primeros', 26572),\n", 2237 | " ('versión', 26542),\n", 2238 | " ('estudios', 26476),\n", 2239 | " ('género', 26442),\n", 2240 | " ('febrero', 26427),\n", 2241 | " ('hoy', 26399),\n", 2242 | " ('disco', 26307),\n", 2243 | " ('último', 26283),\n", 2244 | " ('programa', 26265),\n", 2245 | " ('frente', 26166),\n", 2246 | " ('edad', 26161),\n", 2247 | " ('da', 26156),\n", 2248 | " ('nivel', 26144),\n", 2249 | " ('hacer', 26107),\n", 2250 | " ('siempre', 26074),\n", 2251 | " ('luis', 26019),\n", 2252 | " ('director', 26003),\n", 2253 | " ('batalla', 25983),\n", 2254 | " ('uso', 25918),\n", 2255 | " ('casi', 25872),\n", 2256 | " ('siguiente', 25861),\n", 2257 | " ('ante', 25854),\n", 2258 | " ('juego', 25842),\n", 2259 | " ('isbn', 25839),\n", 2260 | " ('página', 25749),\n", 2261 | " ('española', 25738),\n", 2262 | " ('libro', 25720),\n", 2263 | " ('países', 25709),\n", 2264 | " ('total', 25562),\n", 2265 | " ('cerca', 25328),\n", 2266 | " ('manera', 25277),\n", 2267 | " ('cuales', 25252),\n", 2268 | " ('n', 25165),\n", 2269 | " ('días', 25154),\n", 2270 | " ('mar', 25072),\n", 2271 | " ('francisco', 25065),\n", 2272 | " ('p', 25049),\n", 2273 | " ('construcción', 24902),\n", 2274 | " ('francés', 24830),\n", 2275 | " ('título', 24810),\n", 2276 | " ('chile', 24791),\n", 2277 | " ('principales', 24735),\n", 2278 | " ('división', 24719),\n", 2279 | " ('base', 24685),\n", 2280 | " ('europa', 24672),\n", 2281 | " ('miembros', 24372),\n", 2282 | " ('esa', 24356),\n", 2283 | " ('to', 24326),\n", 2284 | " ('producción', 24158),\n", 2285 | " ('debe', 24102),\n", 2286 | " ('reino', 24047),\n", 2287 | " ('militar', 24035),\n", 2288 | " ('posteriormente', 24011),\n", 2289 | " ('º', 24010),\n", 2290 | " ('fútbol', 23970),\n", 2291 | " ('canciones', 23927),\n", 2292 | " ('www', 23888),\n", 2293 | " ('antonio', 23866),\n", 2294 | " ('comuna', 23703),\n", 2295 | " ('estilo', 23567),\n", 2296 | " ('televisión', 23508),\n", 2297 | " ('información', 23388),\n", 2298 | " ('campo', 23272),\n", 2299 | " ('york', 23183),\n", 2300 | " ('buenos', 23164),\n", 2301 | " ('barcelona', 23075),\n", 2302 | " ('tener', 23023),\n", 2303 | " ('muchas', 23019),\n", 2304 | " ('comenzó', 22845),\n", 2305 | " ('pedro', 22792),\n", 2306 | " ('lado', 22599),\n", 2307 | " ('cuerpo', 22567),\n", 2308 | " ('importantes', 22556),\n", 2309 | " ('metros', 22475),\n", 2310 | " ('mucho', 22471),\n", 2311 | " ('color', 22439),\n", 2312 | " ('john', 22357),\n", 2313 | " ('arte', 22344),\n", 2314 | " ('alto', 22332),\n", 2315 | " ('servicio', 22323),\n", 2316 | " ('porque', 22294),\n", 2317 | " ('tal', 22214),\n", 2318 | " ('mediante', 22131),\n", 2319 | " ('haber', 22010),\n", 2320 | " ('elecciones', 21986),\n", 2321 | " ('tan', 21961),\n", 2322 | " ('incluso', 21941),\n", 2323 | " ('hombre', 21919),\n", 2324 | " ('popular', 21855),\n", 2325 | " ('v', 21767),\n", 2326 | " ('éxito', 21764),\n", 2327 | " ('f', 21745),\n", 2328 | " ('derecho', 21737),\n", 2329 | " ('proyecto', 21702),\n", 2330 | " ('cinco', 21668),\n", 2331 | " ('museo', 21649),\n", 2332 | " ('unión', 21643),\n", 2333 | " ('oeste', 21630),\n", 2334 | " ('r', 21591),\n", 2335 | " ('pesar', 21501),\n", 2336 | " ('finalmente', 21494),\n", 2337 | " ('sino', 21448),\n", 2338 | " ('situada', 21437),\n", 2339 | " ('hombres', 21434),\n", 2340 | " ('costa', 21426),\n", 2341 | " ('social', 21416),\n", 2342 | " ('movimiento', 21414),\n", 2343 | " ('edición', 21375),\n", 2344 | " ('puesto', 21210),\n", 2345 | " ('com', 21205),\n", 2346 | " ('especie', 21201),\n", 2347 | " ('cultura', 21164),\n", 2348 | " ('fuera', 21069),\n", 2349 | " ('localidad', 21052),\n", 2350 | " ('estudio', 20995),\n", 2351 | " ('ambos', 20986),\n", 2352 | " ('|', 20967),\n", 2353 | " ('fin', 20916),\n", 2354 | " ('comunidad', 20910),\n", 2355 | " ('finales', 20877),\n", 2356 | " ('aires', 20876),\n", 2357 | " ('ni', 20852),\n", 2358 | " ('área', 20809),\n", 2359 | " ('l', 20756),\n", 2360 | " ('puerto', 20741),\n", 2361 | " ('demografía', 20725),\n", 2362 | " ('territorio', 20678),\n", 2363 | " ('aún', 20677),\n", 2364 | " ('llamada', 20653),\n", 2365 | " ('sociedad', 20604),\n", 2366 | " ('h', 20578),\n", 2367 | " ('datos', 20540),\n", 2368 | " ('encuentran', 20514),\n", 2369 | " ('éste', 20502),\n", 2370 | " ('etc', 20400),\n", 2371 | " ('cargo', 20283),\n", 2372 | " ('habían', 20240),\n", 2373 | " ('político', 20195),\n", 2374 | " ('grupos', 20097),\n", 2375 | " ('dirección', 20075),\n", 2376 | " ('radio', 20039),\n", 2377 | " ('ello', 19997),\n", 2378 | " ('miembro', 19946),\n", 2379 | " ('nació', 19892),\n", 2380 | " ('término', 19880),\n", 2381 | " ('biografía', 19862),\n", 2382 | " ('original', 19857),\n", 2383 | " ('cualquier', 19830),\n", 2384 | " ('ver', 19825),\n", 2385 | " ('sea', 19817),\n", 2386 | " ('ley', 19792),\n", 2387 | " ('interior', 19676),\n", 2388 | " ('millones', 19656),\n", 2389 | " ('llegó', 19471),\n", 2390 | " ('teatro', 19444),\n", 2391 | " ('proceso', 19440),\n", 2392 | " ('allí', 19380),\n", 2393 | " ('relación', 19319),\n", 2394 | " ('superior', 19222),\n", 2395 | " ('siguientes', 19221),\n", 2396 | " ('lista', 19197),\n", 2397 | " ('voz', 19192),\n", 2398 | " ('oro', 19180),\n", 2399 | " ('manuel', 19131),\n", 2400 | " ('conocida', 19130),\n", 2401 | " ('grande', 19121),\n", 2402 | " ('antiguo', 19091),\n", 2403 | " ('media', 19070),\n", 2404 | " ('propio', 19057),\n", 2405 | " ('alta', 19034),\n", 2406 | " ('pues', 18932),\n", 2407 | " ('juegos', 18831),\n", 2408 | " ('paso', 18827),\n", 2409 | " ('natural', 18807),\n", 2410 | " ('personajes', 18790),\n", 2411 | " ('modo', 18756),\n", 2412 | " ('público', 18756),\n", 2413 | " ('madre', 18684),\n", 2414 | " ('primero', 18638),\n", 2415 | " ('rock', 18609),\n", 2416 | " ('organización', 18531),\n", 2417 | " ('cantón', 18419),\n", 2418 | " ('planta', 18396),\n", 2419 | " ('decir', 18374),\n", 2420 | " ('conjunto', 18349),\n", 2421 | " ('fuerzas', 18332),\n", 2422 | " ('papel', 18258),\n", 2423 | " ('santiago', 18254),\n", 2424 | " ('puntos', 18197),\n", 2425 | " ('alemania', 18189),\n", 2426 | " ('musical', 18183),\n", 2427 | " ('new', 18124),\n", 2428 | " ('dice', 18111),\n", 2429 | " ('américa', 18061),\n", 2430 | " ('edificio', 18054),\n", 2431 | " ('estación', 18051),\n", 2432 | " ('fuerza', 18024),\n", 2433 | " ('alrededor', 17977),\n", 2434 | " ('compañía', 17972),\n", 2435 | " ('iii', 17969),\n", 2436 | " ('aparece', 17938),\n", 2437 | " ('acuerdo', 17877),\n", 2438 | " ('don', 17863),\n", 2439 | " ('última', 17799),\n", 2440 | " ('mujer', 17788),\n", 2441 | " ('igual', 17788),\n", 2442 | " ('cabo', 17783),\n", 2443 | " ('castillo', 17778),\n", 2444 | " ('miguel', 17759),\n", 2445 | " ('cambio', 17750),\n", 2446 | " ('dio', 17728),\n", 2447 | " ('cine', 17716),\n", 2448 | " ('liga', 17671),\n", 2449 | " ('convirtió', 17671),\n", 2450 | " ('ciudades', 17658),\n", 2451 | " ('plantas', 17656)]" 2452 | ] 2453 | }, 2454 | "execution_count": 96, 2455 | "metadata": {}, 2456 | "output_type": "execute_result" 2457 | } 2458 | ], 2459 | "source": [ 2460 | "most_common[:500]" 2461 | ] 2462 | }, 2463 | { 2464 | "cell_type": "code", 2465 | "execution_count": 97, 2466 | "metadata": {}, 2467 | "outputs": [], 2468 | "source": [ 2469 | "import pandas" 2470 | ] 2471 | }, 2472 | { 2473 | "cell_type": "code", 2474 | "execution_count": 99, 2475 | "metadata": {}, 2476 | "outputs": [], 2477 | "source": [ 2478 | "df = pandas.DataFrame(most_common, columns = 'word freq'.split())" 2479 | ] 2480 | }, 2481 | { 2482 | "cell_type": "code", 2483 | "execution_count": 100, 2484 | "metadata": {}, 2485 | "outputs": [ 2486 | { 2487 | "data": { 2488 | "text/html": [ 2489 | "
\n", 2490 | "\n", 2503 | "\n", 2504 | " \n", 2505 | " \n", 2506 | " \n", 2507 | " \n", 2508 | " \n", 2509 | " \n", 2510 | " \n", 2511 | " \n", 2512 | " \n", 2513 | " \n", 2514 | " \n", 2515 | " \n", 2516 | " \n", 2517 | " \n", 2518 | " \n", 2519 | " \n", 2520 | " \n", 2521 | " \n", 2522 | " \n", 2523 | " \n", 2524 | " \n", 2525 | " \n", 2526 | " \n", 2527 | " \n", 2528 | " \n", 2529 | " \n", 2530 | " \n", 2531 | " \n", 2532 | " \n", 2533 | " \n", 2534 | " \n", 2535 | " \n", 2536 | " \n", 2537 | " \n", 2538 | "
wordfreq
0de7768066
1la4042357
2en3389607
3el3047402
4y2648361
\n", 2539 | "
" 2540 | ], 2541 | "text/plain": [ 2542 | " word freq\n", 2543 | "0 de 7768066\n", 2544 | "1 la 4042357\n", 2545 | "2 en 3389607\n", 2546 | "3 el 3047402\n", 2547 | "4 y 2648361" 2548 | ] 2549 | }, 2550 | "execution_count": 100, 2551 | "metadata": {}, 2552 | "output_type": "execute_result" 2553 | } 2554 | ], 2555 | "source": [ 2556 | "df.head()" 2557 | ] 2558 | }, 2559 | { 2560 | "cell_type": "code", 2561 | "execution_count": 106, 2562 | "metadata": {}, 2563 | "outputs": [ 2564 | { 2565 | "data": { 2566 | "text/plain": [ 2567 | "(0, 1000)" 2568 | ] 2569 | }, 2570 | "execution_count": 106, 2571 | "metadata": {}, 2572 | "output_type": "execute_result" 2573 | }, 2574 | { 2575 | "data": { 2576 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEDCAYAAAA849PJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAGnZJREFUeJzt3XtwXvV95/H3V5dH9/vNsmT5AgLjAAGjEi4JZQMkQLawk012oE1JGiae3Skp22bahbabZOkf22x2myYzJI3TEKaZFgrZbOKybIAmpGnTxLEcCPgS24oNtixbd+nR/frdP86R9CBfJJtHOpLO5zXzjM5tzvN7jo+/n3PO7zznMXdHRETiJyPqBoiISDQUACIiMaUAEBGJKQWAiEhMKQBERGJKASAiElORBoCZPWFmHWa2bxHLNpjZy2b2ipm9ZmZ3L0cbRUTWqqjPAJ4E7lzksn8KPOPu1wL3AV9eqkaJiMRBpAHg7j8CelKnmdklZvY9M9trZv9sZltnFgeKw+ESoG0ZmyoisuZkRd2As9gJ/Ed3P2Jm7yI40n8v8FngRTP7JFAA3B5dE0VEVr8VFQBmVgjcBDxrZjOTc8K/9wNPuvv/MrMbgW+a2ZXuPh1BU0VEVr0VFQAEl6T63P2as8x7kLC/wN1/Yma5QCXQsYztExFZM6LuBH4Ld08Cx8zswwAWeGc4+zhwWzj9CiAX6IykoSIia4BF+TRQM3sKuJXgSL4d+AzwA+ArQC2QDTzt7o+Z2Tbga0AhQYfwH7n7i1G0W0RkLYg0AEREJDor6hKQiIgsn8g6gSsrK33Tpk1Rvb2IyKq0d+/eLnevSse6IguATZs20dzcHNXbi4isSmb2ZrrWpUtAIiIxpQAQEYkpBYCISEwpAEREYkoBICISUwoAEZGYUgCIiMTUggGw0M82hg9s+5KZtYQ/1bg9/c0UEZF0W8wZwJOc/2cb7wIaw9cOgge5iYjICrdgAJztZxvnuRf4Gw/8FCg1s9p0NVBERJZGOvoA6oATKeOt4bQzmNkOM2s2s+bOTj3KX0QkSsvaCezuO929yd2bqqrS8iwjERG5SOkIgJPAhpTx+nCaiIisYOkIgF3AA+HdQDcA/e5+Kg3rFRGRJbTg46BTf7bRzFoJfrYxG8Dd/wp4HrgbaAGGgd9ZqsaKiEj6LBgA7n7/AvMd+N20tUhERJaFvgksIhJTCgARkZhSAIiIxJQCQEQkphQAIiIxpQAQEYkpBYCISEwpAEREYkoBICISUwoAEZGYUgCIiMSUAkBEJKYUACIiMaUAEBGJKQWAiEhMKQBERGJKASAiElMKABGRmFIAiIjElAJARCSmFAAiIjGlABARiSkFgIhITCkARERiSgEgIhJTCgARkZhSAIiIxJQCQEQkphQAIiIxpQAQEYkpBYCISEwpAEREYkoBICISU4sKADO708wOmVmLmT1ylvkNZvaymb1iZq+Z2d3pb6qIiKTTggFgZpnA48BdwDbgfjPbNm+xPwWecfdrgfuAL6e7oSIikl6LOQO4Hmhx96PuPg48Ddw7bxkHisPhEqAtfU0UEZGlsJgAqANOpIy3htNSfRb4iJm1As8Dnzzbisxsh5k1m1lzZ2fnRTRXRETSJV2dwPcDT7p7PXA38E0zO2Pd7r7T3ZvcvamqqipNby0iIhdjMQFwEtiQMl4fTkv1IPAMgLv/BMgFKtPRQBERWRqLCYA9QKOZbTazBEEn7655yxwHbgMwsysIAkDXeEREVrAFA8DdJ4GHgBeAgwR3++w3s8fM7J5wsU8BnzCzXwBPAR9zd1+qRouIyNuXtZiF3P15gs7d1GmfThk+ANyc3qaJiMhS0jeBRURiSgEgIhJTCgARkZhSAIiIxJQCQEQkphQAIiIxpQAQEYkpBYCISEwpAEREYkoBICISUwoAEZGYUgCIiMSUAkBEJKYUACIiMaUAEBGJKQWAiEhMKQBERGJKASAiElMKABGRmFIAiIjElAJARCSmFAAiIjGlABARiSkFgIhITCkARERiSgEgIhJTCgARkZhSAIiIxJQCQEQkprKiboCIiJxpbHKK5MgkydEJBkYnSY5MkBydSOt7KABERNLM3RmZmCvgyZGwiIfDydnhMwt8cmSSgdEJxianl7ydCgARkbOYmJomOTJB/8gEfeHfmfH+4XB8fhFPKfBT037e9SeyMijOzaY4L4ui3GyKc7OoK8ujODcrnB5MKwqXKc7Npig3m62fS99nVACIyJo1OTVNcnQyKNrzX8PjZ0zrG54r8kPjU+ddd34ic7aAF+dmU1WUw5aqgnlFPbV4Z4VFPRjOzc5cpq1wbgoAEVnxxien6Rsep3d4gt7hcXqHguG+kfHZo/GZAt6fcrQ+MDZ53vXmZmdQkpdNaV6Ckrxs6svyKVmfHUzLD/7OvIrz5qYX52aTyFr999AsKgDM7E7gi0Am8Nfu/udnWeY/AJ8FHPiFu/9mGtspImuAuzM0PkXv0Dh9M8U8taCnFPm+4Ql6hsbpGx4/79F4IiuD0pRCXVuSy9Z1RZTMK+AlqQU8HM7Jiv4oPEoLBoCZZQKPA3cArcAeM9vl7gdSlmkEHgVudvdeM6teqgaLyMoxMj5F99AYPUPjdA+O0z00Ts/Q2FwxH0op5sPB0fr41Lk7N4tzsygrSFCan6CiMEFjdSGl+QnK8rMpLQj+luUngldBMLwSLqWsVos5A7geaHH3owBm9jRwL3AgZZlPAI+7ey+Au3eku6EisvTOVdDnhsfpHhybHR4+x5F5VobNFu6y/AQbK/K5tqH0LdNK87MpKwiLeXi0npW5+i+rrCaLCYA64ETKeCvwrnnLXAZgZj8muEz0WXf/3vwVmdkOYAdAQ0PDxbRXRC7A+OQ03UNjdA2M0zVbuC+8oCeyMqgoCI7Kywty2FJVSHk4XlEQTJsZLitIUJSThZkt86eVC5WuTuAsoBG4FagHfmRmV7l7X+pC7r4T2AnQ1NR0/nukROSs5hf1zsExOgfG6Boco2twnM6BUboGg3l9w2f/4lAiK4PKggTlYUG/JCzo5WERryjImRsuzKEgkamCvgYtJgBOAhtSxuvDaalagd3uPgEcM7PDBIGwJy2tFFnjpqad7sEx2pNjF13UC3OyqCrKoTK8dn7jlopwPJhWWZRDZVjYVdAFFhcAe4BGM9tMUPjvA+bf4fMd4H7gG2ZWSXBJ6Gg6GyqyGk1PO73D47Qnx2gfGKUjORoMh387BkZpTwbF/WxfHCrMyaKyMEFVUc45i3pVYQ5VRTnqDJULtmAAuPukmT0EvEBwff8Jd99vZo8Bze6+K5z3PjM7AEwBf+ju3UvZcJEouTvJ0cm3FvSBUTpmi/tcgZ+YOrOwlxckqC7KoaY4uGWxpjiX6uJcqouCYl5VGBT5vISKuiwdc4/mUnxTU5M3NzdH8t4iCxkYneBU/2jw6huhrX+U0/0jnOofpa1vhNP9o2e9N70oN4ua4lxqinOoKQqKek1xDuuK54arinJif/+5XDwz2+vuTelYl74JLLEzNDbJqf4R2vpGOd0/Slv/CKf6RjmVDIr96f7RM75BagZVhTnUlubRWF3ELZdVUVuSy7qSPGrCI/nq4hzyE/ovJauH9lZZU6amnY6BUU72jtDaO8LJvuDvqbDIt/WPMDB65uMBKgtzWF+ay+bKAm6+tDIs7rmsL82jtiSX6qLcNfHVf5FUCgBZVSanpjmdHA2K+2yRH54t9m19I2dccy8vSLC+NJcN5fm8a0s5tSVBUa8NC3x1sS7JSDwpAGRFcXe6Bsc53jPM8Z4h3uwe5kTPCK29QZE/nRw9426ZqqIc6svyuLq+lLuurKW+LI+6sjw2lOWxvjRPl2VEzkH/M2TZjU9O09Y3wps9wxzvHuJ4zzBvdg+HRX/4jG+jrivOpb4sj1/bVEZ9WT51ZXlBkS8NCrxufxS5OAoAWRJDY5Mc60ot7nPDbX0jpB7E52Rl0FCeT0N5PjdeUsHG8nwaKvJpKC+gvkwFXmSpKADkok1MTXOiZ5hjXUMc7RziaNcQx7oGOdY1RHty7C3LVhQk2FCez3Uby/jgtXVsKM9nY0UBDeX5VBflkJGhb6WKLDcFgJyXu9M5MEZLZ1DYj3UOBQU/PLpPvR5fXpBgc2UB72msYnNlAZsrC9hYERzZF+VmR/gpRORsFAACBIX+dHKUI+2DHOkY5Ej7wOzfZMptk7nZGWyqKOCK2iI+cFVtUOirCthSWUBpfiLCTyAiF0oBEDPuTlv/aFDg2wc50hEU+pb2wbd8+amiIMGl1YXcc816GquLuLS6kM2VBawrztXlGpE1QgGwhnUNjnHwVJKDp5Icbg+O5ls6Bt/yCIPKwuAhYx/cXselNUU0VhfSWF1IRWFOhC0XkeWgAFgDJqemOdY1xIFTSQ6eGgj/JukcmOuIrS7KobGmkA83baCxppDG6qDYlxXoso1IXCkAVpnk6AQH25LhkX1Q7A+3DzA2GfzOanamBc+qaaziitoittUWc0VtsQq9iJxBAbCCDYxOsO9kktdP9vH6ySSvt/bxRvfw7PzyggTbaot54MaNXBEW+kuqCvXMGhFZFAXACjE4Nsm+k/3sO9nPa63B36NdQ7Pz60rzuKquhA83bWDb+mK21RZTXZSjX3USkYumAIiAu/Nm9zB73+xl7/Fefv5mL4faB5j5aYb1JblcWVfCB7fXcWVdCVfVlahTVkTSTgGwDEbGp3ittS8s9n38/HgvPUPjABTlZHFNQynvf8c6rmko5aq6EipV7EVkGSgAlkD/yAR7jvXw06Pd7Hmjh/1tSSbDb8xuqSzgvVur2d5QxnUby2isLtR99SISCQVAGvQPT/CzN4KCv/tYN/vbkrhDIiuDazaUsuOWLVy3sYxrG8oo1904IrJCKAAuwuTUNK+c6OOfDnXyT4c72dfWP1vwr2so4+HbGrlhSwXXbCjVkyxFZMVSACxSW98IPzocFPx/aeliYHSSzAxje0MpD9/WyI1bKninCr6IrCIKgHNwd/a3JXlx/2lePNDOL08PAFBbkssHrqrl1y+r4qZLKynJ01MuRWR1UgCkmJya5mdv9PDi/nZeOtDOyb4RMgyaNpXzx3dv5dbLq2msLtS99yKyJsQ+ACanpvnJ0W52vdrGSwfb6RueIJGVwS2NlTx8eyO3ba3WPfgisibFMgDcnZ8f7+MfftHGc6+10TU4TlFOFrdvq+H976jhPY1VFOTEctOISIzEqsq1J0d5Zs8Jntl7ghM9IySyMrhtazX3XrOeWy+vVgeuiMTKmg+AqWnnR4c7+bufHecHv+xgatq56ZIKHr7tMt73jhqK9VOFIhJTazYAkqMTPLPnBE/+6xu09o5QWZjgE+/Zwn2/toFNlQVRN09EJHJrLgCOdw/zjX89xrPNrQyOTXL95nIevesK7thWo8cki4ikWDMBcKp/hL986QjP7j1Bhhm/8c71fPzmzVxVXxJ100REVqRVHwD9IxN85Ye/4hs/PoY7fOymzey4ZQvrSnKjbpqIyIq2qgPge/tO8V+/u5+uwTH+3TV1/MEdl7GhPD/qZomIrAqrMgC6B8f44//zOi/sb2dbbTFf/2gTV9eXRt0sEZFVZVG9omZ2p5kdMrMWM3vkPMv9ezNzM2tKXxPfau+bPXzgS//Cy4c6+S93buW7D92s4i8ichEWPAMws0zgceAOoBXYY2a73P3AvOWKgIeB3UvRUHfniR+/wX9//iDrS/P49n+6iSvr1MErInKxFnMGcD3Q4u5H3X0ceBq49yzL/RnwOWA0je0DYHxymt//+1f5s+cO8G+2VvMPn3y3ir+IyNu0mACoA06kjLeG02aZ2XZgg7v/3/OtyMx2mFmzmTV3dnYuqoGDY5N8/Mk9fOfVNj51x2Xs/O3r9AhmEZE0eNudwGaWAfwF8LGFlnX3ncBOgKamJl9o+f7hCT7y9d0cOJXk8x+6mg83bXi7zRURkdBiAuAkkFp568NpM4qAK4Efhs/JXwfsMrN73L35YhuWHJ3ggSd2c+j0AF974Dreu7XmYlclIiJnsZhLQHuARjPbbGYJ4D5g18xMd+9390p33+Tum4CfAm+r+Ls7v/fUK+xvS/Ll39qu4i8isgQWDAB3nwQeAl4ADgLPuPt+M3vMzO5Zikb97e7j/PBQJ5/+jW3cvk3FX0RkKSyqD8Ddnweenzft0+dY9ta306ChsUm+8NJhbtxSwW/fsPHtrEpERM5jxT0e829+8ibdQ+P84Z2X67d3RUSW0IoKgImpab72z0e59fIqtjeURd0cEZE1bUUFwJ5jPfQMjfOb1zdE3RQRkTVvRQXASwfbSWRl8O7GyqibIiKy5q2YAHB3/vFgO+++tJL8xKp8SKmIyKqyYgLgSMcgJ3pGuO2K6qibIiISCysmAHYf7QbglsaqiFsiIhIPKyYAftHaT0VBgvqyvKibIiISCysmAF5r7ePq+hLd+y8iskxWRACMjE9xpGOQq/TLXiIiy2ZFBEBLxyDucMW6oqibIiISGysiAA61DwBwmQJARGTZrIgAONw+QCIrg43l+VE3RUQkNlZEABw6PcClVYVkZa6I5oiIxMKKqLiH2we4XJd/RESWVeQB0D8ywan+US6rUQCIiCynyAPgSNgBfPm6wohbIiISL5EHwOwdQDoDEBFZVpEHwOHTAxTmZFFXqkdAiIgsp8gD4GjXEFuqCvQICBGRZRZ5AJzsG9ED4EREIhBpALg7J3tHqC/TF8BERJZbpAHQOTjG2OS0zgBERCIQaQC09o4AqANYRCQCkQZAW18YADoDEBFZdpEGQEdyDICaotwomyEiEkvRBsDAGNmZRml+dpTNEBGJpWg7gQfGqCrM0XcAREQiEPldQFVFOVE2QUQktiLuAxhVAIiIRCTSAOgaHKNKHcAiIpHIiuqNHegZGtcZgIhIRCI7A5icctyhWgEgIhKJ6AJgehpAZwAiIhFZVACY2Z1mdsjMWszskbPM/wMzO2Bmr5nZ981s40LrnJxyQAEgIhKVBQPAzDKBx4G7gG3A/Wa2bd5irwBN7n418C3gfyy03qnwDKA8P3GBTRYRkXRYzBnA9UCLux9193HgaeDe1AXc/WV3Hw5HfwrUL7TS8ASAotzI+qFFRGJtMQFQB5xIGW8Np53Lg8D/O9sMM9thZs1m1jwwMAhAoQJARCQSae0ENrOPAE3A58823913unuTuzfl5uWTyMwgJysznU0QEZFFWszh90lgQ8p4fTjtLczsduBPgF9397GFVjrlrqN/EZEILeYMYA/QaGabzSwB3AfsSl3AzK4Fvgrc4+4di3nj6WnX9X8RkQgtGADuPgk8BLwAHASecff9ZvaYmd0TLvZ5oBB41sxeNbNd51jdrGl3CnMUACIiUVlUBXb354Hn5037dMrw7Rf6xlPTKABERCIU2TeBp1yXgEREohRZAAR9APolMBGRqER6BqBLQCIi0Yn0DEC3gYqIRCeyAHDUCSwiEqVIfxEsL1vfAhYRiUq0AZBQAIiIRCXSAMhXAIiIREaXgEREYiriMwB1AouIREV9ACIiMaU+ABGRmFIfgIhITOkMQEQkptQHICISU7oLSEQkpiILAAMyMyyqtxcRib3IAiDDVPxFRKIUXQDo6F9EJFIRngFE9c4iIgIRBoB+DlJEJFqRBUBtSW5Uby0iIkR8G6iIiERHASAiElMKABGRmFIAiIjElAJARCSmFAAiIjGlABARiSkFgIhITJm7R/PGZgPAoUjefOWpBLqibsQKoW0xR9tijrbFnMvdvSgdK4rygfyH3L0pwvdfMcysWdsioG0xR9tijrbFHDNrTte6dAlIRCSmFAAiIjEVZQDsjPC9VxptiznaFnO0LeZoW8xJ27aIrBNYRESipUtAIiIxpQAQEYmpSALAzO40s0Nm1mJmj0TRhuViZhvM7GUzO2Bm+83s4XB6uZm9ZGZHwr9l4XQzsy+F2+Y1M9se7SdIPzPLNLNXzOy5cHyzme0OP/Pfm1kinJ4TjreE8zdF2e50M7NSM/uWmf3SzA6a2Y1x3S/M7PfD/x/7zOwpM8uNy35hZk+YWYeZ7UuZdsH7gZl9NFz+iJl9dDHvvewBYGaZwOPAXcA24H4z27bc7VhGk8Cn3H0bcAPwu+HnfQT4vrs3At8PxyHYLo3hawfwleVv8pJ7GDiYMv454AvufinQCzwYTn8Q6A2nfyFcbi35IvA9d98KvJNgm8RuvzCzOuD3gCZ3vxLIBO4jPvvFk8Cd86Zd0H5gZuXAZ4B3AdcDn5kJjfNy92V9ATcCL6SMPwo8utztiOoFfBe4g+Bb0LXhtFqCL8YBfBW4P2X52eXWwguoD3fo9wLPAUbwDc+s+fsH8AJwYzicFS5nUX+GNG2HEuDY/M8Tx/0CqANOAOXhv/NzwPvjtF8Am4B9F7sfAPcDX02Z/pblzvWK4hLQzD/2jNZw2poXnqpeC+wGatz9VDjrNFATDq/17fOXwB8B0+F4BdDn7pPheOrnnd0W4fz+cPm1YDPQCXwjvBz212ZWQAz3C3c/CfxP4DhwiuDfeS/x3C9mXOh+cFH7hzqBl4mZFQL/G/jP7p5MnedBZK/5+3HN7N8CHe6+N+q2rABZwHbgK+5+LTDE3Gk+EKv9ogy4lyAU1wMFnHlJJLaWcj+IIgBOAhtSxuvDaWuWmWUTFP+/dfdvh5Pbzaw2nF8LdITT1/L2uRm4x8zeAJ4muAz0RaDUzGaeS5X6eWe3RTi/BOhezgYvoVag1d13h+PfIgiEOO4XtwPH3L3T3SeAbxPsK3HcL2Zc6H5wUftHFAGwB2gMe/gTBJ09uyJox7IwMwO+Dhx0979ImbULmOmp/yhB38DM9AfC3v4bgP6UU8FVzd0fdfd6d99E8O/+A3f/LeBl4EPhYvO3xcw2+lC4/Jo4Inb308AJM7s8nHQbcIAY7hcEl35uMLP88P/LzLaI3X6R4kL3gxeA95lZWXhG9b5w2vlF1OFxN3AY+BXwJ1F3wCzxZ303wenba8Cr4etugmuW3weOAP8IlIfLG8FdUr8CXie4MyLyz7EE2+VW4LlweAvwM6AFeBbICafnhuMt4fwtUbc7zdvgGqA53De+A5TFdb8A/hvwS2Af8E0gJy77BfAUQd/HBMGZ4YMXsx8AHw+3SQvwO4t5bz0KQkQkptQJLCISUwoAEZGYUgCIiMSUAkBEJKYUACIiMaUAEBGJKQWAiEhM/X+KJ6Bn2kmxCQAAAABJRU5ErkJggg==\n", 2577 | "text/plain": [ 2578 | "" 2579 | ] 2580 | }, 2581 | "metadata": {}, 2582 | "output_type": "display_data" 2583 | } 2584 | ], 2585 | "source": [ 2586 | "df.freq.cumsum().plot()\n", 2587 | "xlim(0,1000)" 2588 | ] 2589 | }, 2590 | { 2591 | "cell_type": "code", 2592 | "execution_count": 107, 2593 | "metadata": {}, 2594 | "outputs": [ 2595 | { 2596 | "data": { 2597 | "text/plain": [ 2598 | "60.0" 2599 | ] 2600 | }, 2601 | "execution_count": 107, 2602 | "metadata": {}, 2603 | "output_type": "execute_result" 2604 | } 2605 | ], 2606 | "source": [ 2607 | "3000/50" 2608 | ] 2609 | }, 2610 | { 2611 | "cell_type": "code", 2612 | "execution_count": null, 2613 | "metadata": {}, 2614 | "outputs": [], 2615 | "source": [] 2616 | } 2617 | ], 2618 | "metadata": { 2619 | "kernelspec": { 2620 | "display_name": "Python 3", 2621 | "language": "python", 2622 | "name": "python3" 2623 | }, 2624 | "language_info": { 2625 | "codemirror_mode": { 2626 | "name": "ipython", 2627 | "version": 3 2628 | }, 2629 | "file_extension": ".py", 2630 | "mimetype": "text/x-python", 2631 | "name": "python", 2632 | "nbconvert_exporter": "python", 2633 | "pygments_lexer": "ipython3", 2634 | "version": "3.6.3" 2635 | } 2636 | }, 2637 | "nbformat": 4, 2638 | "nbformat_minor": 2 2639 | } 2640 | --------------------------------------------------------------------------------