{ "cells": [ { "cell_type": "code", "execution_count": 7, "id": "95956dfc-c447-4dcb-a3c4-563ec91e9211", "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 8, "id": "8724a364-ae3a-41a1-9b4a-68d53c452d83", "metadata": {}, "outputs": [], "source": [ "infile = \"/Users/carolanderson/Dropbox/Existing2022CardInventoryWithNewBoxes2023.txt\"\n", "df= pd.read_csv(infile, sep=\"\\t\", encoding=\"ISO-8859-1\")" ] }, { "cell_type": "code", "execution_count": 9, "id": "660ed1bf-cf66-495e-a829-cfe37861aa3f", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
TypeSportYearCompanyProductCard #Player NameNotesHOFGraderGradeStorage Box
0CardBaseball1949LeafNaN68Eddie MillerSPNaNBeckett3.0270.0
1CardBaseball1949LeafNaN48Johnny SchmitzSPNaNBeckett3.0270.0
2CardBaseball1961ToppsNaN575Ernie BanksASNaNBeckett4.5269.0
3CardBaseball1949LeafNaN129Kirby HigbeSPNaNBeckett1.5270.0
4CardBaseball1999ToppsAll-Topps Mystery FinestM3Mark McGwireNaNNaNBeckett9.0270.0
\n", "
" ], "text/plain": [ " Type Sport Year Company Product Card # \\\n", "0 Card Baseball 1949 Leaf NaN 68 \n", "1 Card Baseball 1949 Leaf NaN 48 \n", "2 Card Baseball 1961 Topps NaN 575 \n", "3 Card Baseball 1949 Leaf NaN 129 \n", "4 Card Baseball 1999 Topps All-Topps Mystery Finest M3 \n", "\n", " Player Name Notes HOF Grader Grade Storage Box \n", "0 Eddie Miller SP NaN Beckett 3.0 270.0 \n", "1 Johnny Schmitz SP NaN Beckett 3.0 270.0 \n", "2 Ernie Banks AS NaN Beckett 4.5 269.0 \n", "3 Kirby Higbe SP NaN Beckett 1.5 270.0 \n", "4 Mark McGwire NaN NaN Beckett 9.0 270.0 " ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head()" ] }, { "cell_type": "code", "execution_count": 13, "id": "d37f49f3-8fca-42db-a148-b0d0c37c9c04", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
TypeSportYearCompanyProductCard #Player NameNotesHOFGraderGradeStorage Box
55CardBaseball1952BowmanNaN11Ralph KinerNaNYBeckett3.0271.0
403CardBaseball1953BowmanColor80Ralph KinerNaNNaNNaNNaNNaN
314CardBaseball1949LeafNaN61Jake EarlyNaNNaNNaNNaNNaN
179CardBaseball1985ToppsNaN401Mark McGwireRookieNaNSportscard Guaranty86.0268.0
492CardBaseball1952BowmanNaN122Joe GaragiolaNaNNaNNaNNaNNaN
315CardBaseball1948LeafNaN49Del EnnisNaNNaNNaNNaNNaN
109CardBaseball1949LeafNaN62Eddie JoostSPNaNBeckett2.5270.0
66CardBaseball1949LeafNaN113Dutch LeonardSPNaNBeckett2.5268.0
340CardBasketball1994Competitive ImagesNaN8Michael JordanNaNNaNNaNNaNNaN
104CardBaseball1949LeafNaN36Al ZarillaSPNaNBeckett2.5271.0
469CardBaseball1974ToppsNaN230Tony PerezNaNNaNNaNNaNNaN
420CardBaseball1951BowmanNaN110Bobby BrownNaNNaNNaNNaNNaN
302CardBaseball2017ToppsNowOS-80Shohei OhtaniNaNNaNNaNNaNNaN
197CardBaseball1957ToppsNaN25Whitey FordNaNNaNSportscard Guaranty86.0NaN
144CardBaseball1954Dan-DeeNaN3Walker CooperNaNNaNBeckett2.0270.0
481CardBaseball1952BowmanNaN96Ralph BrancaNaNNaNNaNNaNNaN
194CardBaseball1987FleerUpdate GlossyU-68Greg MadduxRookieNaNSportscard Guaranty96.0268.0
123CardBaseball2001ToppsNaN726Ichiro SuzukiNaNNaNBeckett8.0267.0
224CardBaseball1993ClassicBestPR1Derek JeterNaNNaNCSA9.0NaN
358CardBaseball1952ToppsNaN36Gil HodgesNaNNaNNaNNaNNaN
\n", "
" ], "text/plain": [ " Type Sport Year Company Product Card # \\\n", "55 Card Baseball 1952 Bowman NaN 11 \n", "403 Card Baseball 1953 Bowman Color 80 \n", "314 Card Baseball 1949 Leaf NaN 61 \n", "179 Card Baseball 1985 Topps NaN 401 \n", "492 Card Baseball 1952 Bowman NaN 122 \n", "315 Card Baseball 1948 Leaf NaN 49 \n", "109 Card Baseball 1949 Leaf NaN 62 \n", "66 Card Baseball 1949 Leaf NaN 113 \n", "340 Card Basketball 1994 Competitive Images NaN 8 \n", "104 Card Baseball 1949 Leaf NaN 36 \n", "469 Card Baseball 1974 Topps NaN 230 \n", "420 Card Baseball 1951 Bowman NaN 110 \n", "302 Card Baseball 2017 Topps Now OS-80 \n", "197 Card Baseball 1957 Topps NaN 25 \n", "144 Card Baseball 1954 Dan-Dee NaN 3 \n", "481 Card Baseball 1952 Bowman NaN 96 \n", "194 Card Baseball 1987 Fleer Update Glossy U-68 \n", "123 Card Baseball 2001 Topps NaN 726 \n", "224 Card Baseball 1993 Classic Best PR1 \n", "358 Card Baseball 1952 Topps NaN 36 \n", "\n", " Player Name Notes HOF Grader Grade Storage Box \n", "55 Ralph Kiner NaN Y Beckett 3.0 271.0 \n", "403 Ralph Kiner NaN NaN NaN NaN NaN \n", "314 Jake Early NaN NaN NaN NaN NaN \n", "179 Mark McGwire Rookie NaN Sportscard Guaranty 86.0 268.0 \n", "492 Joe Garagiola NaN NaN NaN NaN NaN \n", "315 Del Ennis NaN NaN NaN NaN NaN \n", "109 Eddie Joost SP NaN Beckett 2.5 270.0 \n", "66 Dutch Leonard SP NaN Beckett 2.5 268.0 \n", "340 Michael Jordan NaN NaN NaN NaN NaN \n", "104 Al Zarilla SP NaN Beckett 2.5 271.0 \n", "469 Tony Perez NaN NaN NaN NaN NaN \n", "420 Bobby Brown NaN NaN NaN NaN NaN \n", "302 Shohei Ohtani NaN NaN NaN NaN NaN \n", "197 Whitey Ford NaN NaN Sportscard Guaranty 86.0 NaN \n", "144 Walker Cooper NaN NaN Beckett 2.0 270.0 \n", "481 Ralph Branca NaN NaN NaN NaN NaN \n", "194 Greg Maddux Rookie NaN Sportscard Guaranty 96.0 268.0 \n", "123 Ichiro Suzuki NaN NaN Beckett 8.0 267.0 \n", "224 Derek Jeter NaN NaN CSA 9.0 NaN \n", "358 Gil Hodges NaN NaN NaN NaN NaN " ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "sample = df[:500].sample(20)\n", "sample" ] }, { "cell_type": "code", "execution_count": 15, "id": "795ef99b-abd7-4fe8-b56c-1779ebda8d52", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
TypeSportYearCompanyProductCard #Player NameNotesHOFGraderGradeStorage Box
179CardBaseball1985ToppsNaN401Mark McGwireRookieNaNSportscard Guaranty86.0268.0
492CardBaseball1952BowmanNaN122Joe GaragiolaNaNNaNNaNNaNNaN
315CardBaseball1948LeafNaN49Del EnnisNaNNaNNaNNaNNaN
109CardBaseball1949LeafNaN62Eddie JoostSPNaNBeckett2.5270.0
66CardBaseball1949LeafNaN113Dutch LeonardSPNaNBeckett2.5268.0
340CardBasketball1994Competitive ImagesNaN8Michael JordanNaNNaNNaNNaNNaN
104CardBaseball1949LeafNaN36Al ZarillaSPNaNBeckett2.5271.0
\n", "
" ], "text/plain": [ " Type Sport Year Company Product Card # \\\n", "179 Card Baseball 1985 Topps NaN 401 \n", "492 Card Baseball 1952 Bowman NaN 122 \n", "315 Card Baseball 1948 Leaf NaN 49 \n", "109 Card Baseball 1949 Leaf NaN 62 \n", "66 Card Baseball 1949 Leaf NaN 113 \n", "340 Card Basketball 1994 Competitive Images NaN 8 \n", "104 Card Baseball 1949 Leaf NaN 36 \n", "\n", " Player Name Notes HOF Grader Grade Storage Box \n", "179 Mark McGwire Rookie NaN Sportscard Guaranty 86.0 268.0 \n", "492 Joe Garagiola NaN NaN NaN NaN NaN \n", "315 Del Ennis NaN NaN NaN NaN NaN \n", "109 Eddie Joost SP NaN Beckett 2.5 270.0 \n", "66 Dutch Leonard SP NaN Beckett 2.5 268.0 \n", "340 Michael Jordan NaN NaN NaN NaN NaN \n", "104 Al Zarilla SP NaN Beckett 2.5 271.0 " ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "sample[3:10]" ] }, { "cell_type": "code", "execution_count": 23, "id": "58a90d8e-0480-4187-a7eb-cd69463c0329", "metadata": {}, "outputs": [], "source": [ "outfile = \"sample_data/sample_data_1.txt\"\n", "sample[3:13].to_csv(outfile, sep=\"\\t\", index=False, encoding=\"utf-8\")" ] }, { "cell_type": "code", "execution_count": 21, "id": "31083cda-058b-4aee-b0d5-965e48c4bca7", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
animalcoat patternQuantity
0Leopardspots2
1Tigerstripes10
2Lionsolid1
3Cheetahspots1
\n", "
" ], "text/plain": [ " animal coat pattern Quantity\n", "0 Leopard spots 2\n", "1 Tiger stripes 10\n", "2 Lion solid 1\n", "3 Cheetah spots 1" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df2 = pd.DataFrame([{\"animal\": \"Leopard\", \"coat pattern\": \"spots\", \"Quantity\" : 2},\n", " {\"animal\": \"Tiger\", \"coat pattern\": \"stripes\", \"Quantity\" : 10},\n", " {\"animal\" : \"Lion\", \"coat pattern\" : \"solid\", \"Quantity\" : 1},\n", " {\"animal\" : \"Cheetah\", \"coat pattern\" : \"spots\", \"Quantity\" : 1}])\n", "\n", "df2" ] }, { "cell_type": "code", "execution_count": 22, "id": "bc9735c0-e12a-4b1f-8cb2-7501d37a4c19", "metadata": {}, "outputs": [], "source": [ "outfile = \"sample_data/sample_data_2.txt\"\n", "df2.to_csv(outfile, sep=\"\\t\", index=False)" ] }, { "cell_type": "code", "execution_count": 20, "id": "ed438bbb-03f4-44a9-8f14-9390f3996cae", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\"animal\" in df2" ] }, { "cell_type": "code", "execution_count": 29, "id": "36d5bb2e-cc1e-4afa-bff9-730832e9a5ae", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dtype('int64')" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df3 = pd.read_csv(\"sample_data/sample_data_1.txt\", sep=\"\\t\", encoding=\"ISO-8859-1\" )\n", "df3.Year.dtype" ] }, { "cell_type": "code", "execution_count": null, "id": "905c63e9-3d06-4905-ac63-3e66bf94c22e", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python [conda env:rebalance] *", "language": "python", "name": "conda-env-rebalance-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.13" } }, "nbformat": 4, "nbformat_minor": 5 }