diff --git a/dataeng/processed_data/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/dataeng/processed_data/.ipynb_checkpoints/Untitled-checkpoint.ipynb new file mode 100644 index 00000000..75a77b9a --- /dev/null +++ b/dataeng/processed_data/.ipynb_checkpoints/Untitled-checkpoint.ipynb @@ -0,0 +1,216 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "path_to_folder = \"../02-src-data/\"\n", + "path_to_img = \"https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/\"\n", + "src_data = os.listdir(path_to_folder)" + ] + }, + { + "cell_type": "code", + "execution_count": 112, + "metadata": {}, + "outputs": [], + "source": [ + "data_csv, data_img, user_ids = set(), set(), set()\n", + "for file in src_data:\n", + " if file.endswith(\".csv\"):\n", + " user_ids.add(file[:-4])\n", + " data_csv.add(file)\n", + " else:\n", + " data_img.add(file)" + ] + }, + { + "cell_type": "code", + "execution_count": 113, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "output_data = pd.DataFrame(columns=['id'])\n", + "for csv in data_csv:\n", + " output_data.append({'id': csv[:-4]}, ignore_index=True)\n", + " \n", + " csv_file = pd.read_csv(path_to_folder + csv)\n", + "# row = pd.DataFrame(csv_file)\n", + " output_data = output_data.append(csv_file, ignore_index=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 114, + "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", + "
birthtslast_namefirst_nameid
05.065524e+11KirkRobertNaN
17.857108e+11SmithAmyNaN
23.400596e+11QuickWilliamNaN
39.712080e+11MillerChadNaN
47.858836e+11HardinChristopherNaN
...............
956.706260e+11GarciaRosaNaN
969.559152e+11RaymondAdolphNaN
971.018469e+12ShoupJeanneNaN
981.074805e+12MillerDinoNaN
998.213940e+11FolkersEllenNaN
\n", + "

100 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " birthts last_name first_name id\n", + "0 5.065524e+11 Kirk Robert NaN\n", + "1 7.857108e+11 Smith Amy NaN\n", + "2 3.400596e+11 Quick William NaN\n", + "3 9.712080e+11 Miller Chad NaN\n", + "4 7.858836e+11 Hardin Christopher NaN\n", + ".. ... ... ... ...\n", + "95 6.706260e+11 Garcia Rosa NaN\n", + "96 9.559152e+11 Raymond Adolph NaN\n", + "97 1.018469e+12 Shoup Jeanne NaN\n", + "98 1.074805e+12 Miller Dino NaN\n", + "99 8.213940e+11 Folkers Ellen NaN\n", + "\n", + "[100 rows x 4 columns]" + ] + }, + "execution_count": 114, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "output_data" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.10" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/dataeng/processed_data/answers.txt b/dataeng/processed_data/answers.txt new file mode 100644 index 00000000..7b1f2126 --- /dev/null +++ b/dataeng/processed_data/answers.txt @@ -0,0 +1,108 @@ +===================== PYTHON ====================== + +1. Optimise execution time of this Python code snippet: + +def count_connections(list1: list, list2: list) -> int: + return len(list(set(list1) & set(list2))) + +2. Given a string S, find the length of the longest substring without repeating characters. Analyze your solution and please provide Space and Time complexities. + +def longestSubstring(s: str) -> int: + stored = "" + searched = "" + for letter in s: + if letter not in searched: + searched += letter + else: + if len(stored) < len(searched): + stored = searched + searched += letter + searched = searched[searched.index(letter)+1:] + return(max(len(stored), len(searched))) + +3. Given a sorted array of distinct integers and a target value, return the index if the target is found. If not, return the index where it would be if it were inserted in order. + +def foo(t, arr): + if t not in arr: + prevNum = min(arr, key=lambda x:abs(x-t)) + if prevNum > t: + return arr.index(prevNum) + return arr.index(prevNum) + 1 + return arr.index(t) + +===================== SQL ======================= + +1. Rewrite this SQL without subquery: + +SELECT id +FROM users +WHERE id NOT IN ( + SELECT user_id + FROM departments + WHERE department_id = 1 +); + +SELECT id +FROM users +JOIN departments ON id=user_id AND department_id!=1 + +2. Write a SQL query to find all duplicate lastnames in a table named user + ++----+-----------+----------- +| id | firstname | lastname | ++----+-----------+----------- +| 1 | Ivan | Sidorov | +| 2 | Alexandr | Ivanov | +| 3 | Petr | Petrov | +| 4 | Stepan | Ivanov | ++----+-----------+----------+ + +SELECT lastname +FROM user +GROUP BY lastname +HAVING COUNT(lastname)>1; + +3. Write a SQL query to get a username from the user table with the second highest salary from salary tables. Show the username and it's salary in the result. + ++---------+--------+ +| user_id | salary | ++----+--------+----+ +| 1 | 1000 | +| 2 | 1100 | +| 3 | 900 | +| 4 | 1200 | ++---------+--------+ + ++---------+--------+ +| id | username | ++----+--------+----+ +| 1 | Alex | +| 2 | Maria | +| 3 | Bob | +| 4 | Sean | ++---------+-------+ + +SELECT username, salary +FROM user, salary +WHERE user_id=id +ORDER BY salary DESC +LIMIT 1 OFFSET 1; + +===================== LINUX ====================== + +1. List processes listening on ports 80 and 443 + +ss -tunlp | grep :80 +ss -tunlp | grep :443 + +2. List process environment variables by given PID + +cat /proc//environ + +3. Launch a python program my_program.py through CLI in the background. How would you close it after some period of time? + +- get pid: + ps aux | grep my_program.py + +- kill the process: + kill -9 diff --git a/dataeng/processed_data/level 1/README.md b/dataeng/processed_data/level 1/README.md new file mode 100644 index 00000000..132b4c01 --- /dev/null +++ b/dataeng/processed_data/level 1/README.md @@ -0,0 +1 @@ +The main script makes requests to given folder, processes data and by using Pandas library makes a dataframe with necessary information and saves the dataframe to csv-file named output.csv. diff --git a/dataeng/processed_data/level 1/output.csv b/dataeng/processed_data/level 1/output.csv new file mode 100644 index 00000000..4a8aa58d --- /dev/null +++ b/dataeng/processed_data/level 1/output.csv @@ -0,0 +1,101 @@ +,user_id,first_name,last_name,birthts,img_path +0,1000,Susan,Lee,612302400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1000.png +1,1001,Rosa,Garcia,670626000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1001.png +2,1002,Nathan,Emery,697237200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1002.png +3,1003,Vernon,Evans,633733200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1003.png +4,1004,Maria,Crooks,1051214400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1004.png +5,1005,Sharon,Lang,700606800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1005.png +6,1006,Rick,Mayfield,412549200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1006.png +7,1007,Eddie,Baumbach,874526400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1007.png +8,1008,Coletta,Haring,768081600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1008.png +9,1009,Margaret,Smith,388612800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1009.png +10,1010,James,Martin,879627600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1010.png +11,1011,Glen,Martin,636066000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1011.png +12,1012,Debbie,Mooney,423086400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1012.png +13,1013,Shaneka,Cook,752533200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1013.png +14,1014,Kim,Moore,403218000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1014.png +15,1015,Lorraine,Bingham,891288000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1015.png +16,1016,Betty,Partin,467240400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1016.png +17,1017,Lewis,Erickson,642283200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1017.png +18,1018,Jenee,Crouse,429566400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1018.png +19,1019,Wendy,Jarrette,650145600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1019.png +20,1020,Becky,Hanner,883429200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1020.png +21,1021,Ray,Nunes,352501200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1021.png +22,1022,John,Rose,919630800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1022.png +23,1023,Michael,Diaz,630277200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1023.png +24,1024,William,Quick,340059600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1024.png +25,1025,Dino,Miller,1074805200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1025.png +26,1026,James,Henry,954705600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1026.png +27,1027,Gregory,Pittman,398894400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1027.png +28,1028,Martha,Burwell,503269200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1028.png +29,1029,Jimmy,Deane,947365200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1029.png +30,1030,Kathleen,Gittens,921272400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1030.png +31,1031,Sidney,Woods,865972800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1031.png +32,1032,Robert,David,666997200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1032.png +33,1033,Jeanne,Shoup,1018468800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1033.png +34,1034,Brenda,Croyle,788302800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1034.png +35,1035,Adolph,Raymond,955915200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1035.png +36,1036,Ellen,Folkers,821394000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1036.png +37,1037,Patrick,Newell,853794000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1037.png +38,1038,Mary,Roman,750891600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1038.png +39,1039,Danielle,Robinson,887230800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1039.png +40,1040,Clara,Kimble,765403200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1040.png +41,1041,David,Bailey,1062446400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1041.png +42,1042,James,Nance,1063051200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1042.png +43,1043,John,Ramage,378507600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1043.png +44,1044,Christopher,Hardin,785883600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1044.png +45,1045,Suzanne,Ferguson,812581200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1045.png +46,1046,Margaret,Diaz,942872400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1046.png +47,1047,Kenneth,Osborn,793918800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1047.png +48,1048,Larry,Sanchez,1068930000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1048.png +49,1049,Brian,Brown,814050000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1049.png +50,1050,Warren,Green,443048400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1050.png +51,1051,Janet,Chavarria,1087588800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1051.png +52,1052,Carolyn,Seymore,385851600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1052.png +53,1053,Dorothy,Massey,356990400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1053.png +54,1054,Melissa,Denny,482011200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1054.png +55,1055,Jaclyn,Adams,614635200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1055.png +56,1056,Frances,Visher,906580800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1056.png +57,1057,Chad,Miller,971208000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1057.png +58,1058,Olivia,Stout,690674400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1058.png +59,1059,Wallace,Miller,821134800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1059.png +60,1060,Judith,Hatchett,925070400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1060.png +61,1061,Madelyn,Oliver,936907200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1061.png +62,1062,Robert,Kirk,506552400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1062.png +63,1063,Stephanie,Nelson,476571600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1063.png +64,1064,Barbara,Blankenship,655506000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1064.png +65,1065,Matthew,Bloom,531176400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1065.png +66,1066,Jeffrey,Mcdonald,686091600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1066.png +67,1067,Joseph,Carter,1081713600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1067.png +68,1068,Eloy,Florentino,848005200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1068.png +69,1069,David,Myles,432676800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1069.png +70,1070,Elizabeth,Hoover,334702800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1070.png +71,1071,Jerome,Weaver,1008795600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1071.png +72,1072,Morris,Hall,407019600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1072.png +73,1073,Myrtle,Ferro,840830400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1073.png +74,1074,Gisela,Patterson,464990400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1074.png +75,1075,Stacey,Bishop,493848000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1075.png +76,1076,Ray,Goins,933451200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1076.png +77,1077,Blake,Dickerson,508107600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1077.png +78,1078,David,May,601074000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1078.png +79,1079,Cindy,Wilcox,1021060800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1079.png +80,1080,Mary,Nelson,518644800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1080.png +81,1081,Amy,Smith,785710800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1081.png +82,1082,Joseph,Denton,463089600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1082.png +83,1083,Keith,Wiggin,461707200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1083.png +84,1084,Jody,Hochmuth,752446800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1084.png +85,1085,Beverly,Livesey,739224000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1085.png +86,1086,Nicole,Pharr,884552400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1086.png +87,1087,Aaron,Fox,1090094400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1087.png +88,1088,Rachel,Robinson,528148800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1088.png +89,1089,Leah,Costales,1072472400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1089.png +90,1090,Thomas,Williams,946501200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1090.png +91,1091,Opal,Morse,463780800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1091.png +92,1092,Alan,Mcgraw,469054800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1092.png +93,1093,Aaron,Towe,877809600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1093.png +94,1094,Cecil,Struck,416437200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1094.png +95,1095,Corey,Davis,1054411200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1095.png +96,1096,James,Peacock,503442000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1096.png +97,1097,John,Bausch,1013029200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1097.png +98,1098,Maria,Horton,702504000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1098.png +99,1099,Samuel,Ladner,815259600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1099.png diff --git a/dataeng/processed_data/level 1/script.py b/dataeng/processed_data/level 1/script.py new file mode 100644 index 00000000..333eee04 --- /dev/null +++ b/dataeng/processed_data/level 1/script.py @@ -0,0 +1,36 @@ +import requests +import re +import pandas as pd + +# source path +path_to_folder = "https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/" + +# preparing dataframe with column names +output_data = pd.DataFrame(columns=["user_id", "first_name", "last_name", "birthts", "img_path"]) + +# bad approach, because indexes are hard coded +for i in range(1000, 1100): + + # making requests. it takes about 15-20 seconds to make 100 of them + r = requests.get(path_to_folder + str(i) + ".csv") + + # decoding given raw information + content = r.content.decode("utf-8") + content = re.findall(r'\w+', content) + + # preparing a row with info for the dataframe + row = { + 'user_id': i, + 'first_name': content[3], + 'last_name': content[4], + 'birthts': content[5], + 'img_path': path_to_folder + str(i) + ".png" + } + + row = pd.Series(row) + + # putting info into dataframe + output_data = output_data.append(row, ignore_index=True) + +# saving dataframe as a csv-file +output_data.to_csv("./output.csv") diff --git a/dataeng/processed_data/level 2/README.md b/dataeng/processed_data/level 2/README.md new file mode 100644 index 00000000..e0a12076 --- /dev/null +++ b/dataeng/processed_data/level 2/README.md @@ -0,0 +1,3 @@ +In this case basic http server is used. The server uses port 80 and works the way it is described in official Python Documentation. It works with HTML-file named index.html and CSV-file named output.csv which was also used previously at Level 1. + +HTML-file parses the CSV-file and presents it as a table. diff --git a/dataeng/processed_data/level 2/index.html b/dataeng/processed_data/level 2/index.html new file mode 100644 index 00000000..94ff2fed --- /dev/null +++ b/dataeng/processed_data/level 2/index.html @@ -0,0 +1,71 @@ + + + + + + + +
+ + + + + \ No newline at end of file diff --git a/dataeng/processed_data/level 2/main.py b/dataeng/processed_data/level 2/main.py new file mode 100644 index 00000000..acca8646 --- /dev/null +++ b/dataeng/processed_data/level 2/main.py @@ -0,0 +1,10 @@ +import http.server +import socketserver + +PORT = 80 + +Handler = http.server.SimpleHTTPRequestHandler + +with socketserver.TCPServer(("", PORT), Handler) as httpd: + print("serving at port", PORT) + httpd.serve_forever() \ No newline at end of file diff --git a/dataeng/processed_data/level 2/output.csv b/dataeng/processed_data/level 2/output.csv new file mode 100644 index 00000000..4a8aa58d --- /dev/null +++ b/dataeng/processed_data/level 2/output.csv @@ -0,0 +1,101 @@ +,user_id,first_name,last_name,birthts,img_path +0,1000,Susan,Lee,612302400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1000.png +1,1001,Rosa,Garcia,670626000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1001.png +2,1002,Nathan,Emery,697237200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1002.png +3,1003,Vernon,Evans,633733200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1003.png +4,1004,Maria,Crooks,1051214400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1004.png +5,1005,Sharon,Lang,700606800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1005.png +6,1006,Rick,Mayfield,412549200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1006.png +7,1007,Eddie,Baumbach,874526400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1007.png +8,1008,Coletta,Haring,768081600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1008.png +9,1009,Margaret,Smith,388612800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1009.png +10,1010,James,Martin,879627600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1010.png +11,1011,Glen,Martin,636066000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1011.png +12,1012,Debbie,Mooney,423086400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1012.png +13,1013,Shaneka,Cook,752533200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1013.png +14,1014,Kim,Moore,403218000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1014.png +15,1015,Lorraine,Bingham,891288000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1015.png +16,1016,Betty,Partin,467240400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1016.png +17,1017,Lewis,Erickson,642283200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1017.png +18,1018,Jenee,Crouse,429566400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1018.png +19,1019,Wendy,Jarrette,650145600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1019.png +20,1020,Becky,Hanner,883429200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1020.png +21,1021,Ray,Nunes,352501200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1021.png +22,1022,John,Rose,919630800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1022.png +23,1023,Michael,Diaz,630277200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1023.png +24,1024,William,Quick,340059600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1024.png +25,1025,Dino,Miller,1074805200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1025.png +26,1026,James,Henry,954705600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1026.png +27,1027,Gregory,Pittman,398894400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1027.png +28,1028,Martha,Burwell,503269200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1028.png +29,1029,Jimmy,Deane,947365200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1029.png +30,1030,Kathleen,Gittens,921272400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1030.png +31,1031,Sidney,Woods,865972800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1031.png +32,1032,Robert,David,666997200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1032.png +33,1033,Jeanne,Shoup,1018468800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1033.png +34,1034,Brenda,Croyle,788302800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1034.png +35,1035,Adolph,Raymond,955915200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1035.png +36,1036,Ellen,Folkers,821394000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1036.png +37,1037,Patrick,Newell,853794000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1037.png +38,1038,Mary,Roman,750891600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1038.png +39,1039,Danielle,Robinson,887230800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1039.png +40,1040,Clara,Kimble,765403200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1040.png +41,1041,David,Bailey,1062446400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1041.png +42,1042,James,Nance,1063051200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1042.png +43,1043,John,Ramage,378507600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1043.png +44,1044,Christopher,Hardin,785883600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1044.png +45,1045,Suzanne,Ferguson,812581200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1045.png +46,1046,Margaret,Diaz,942872400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1046.png +47,1047,Kenneth,Osborn,793918800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1047.png +48,1048,Larry,Sanchez,1068930000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1048.png +49,1049,Brian,Brown,814050000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1049.png +50,1050,Warren,Green,443048400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1050.png +51,1051,Janet,Chavarria,1087588800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1051.png +52,1052,Carolyn,Seymore,385851600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1052.png +53,1053,Dorothy,Massey,356990400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1053.png +54,1054,Melissa,Denny,482011200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1054.png +55,1055,Jaclyn,Adams,614635200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1055.png +56,1056,Frances,Visher,906580800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1056.png +57,1057,Chad,Miller,971208000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1057.png +58,1058,Olivia,Stout,690674400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1058.png +59,1059,Wallace,Miller,821134800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1059.png +60,1060,Judith,Hatchett,925070400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1060.png +61,1061,Madelyn,Oliver,936907200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1061.png +62,1062,Robert,Kirk,506552400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1062.png +63,1063,Stephanie,Nelson,476571600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1063.png +64,1064,Barbara,Blankenship,655506000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1064.png +65,1065,Matthew,Bloom,531176400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1065.png +66,1066,Jeffrey,Mcdonald,686091600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1066.png +67,1067,Joseph,Carter,1081713600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1067.png +68,1068,Eloy,Florentino,848005200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1068.png +69,1069,David,Myles,432676800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1069.png +70,1070,Elizabeth,Hoover,334702800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1070.png +71,1071,Jerome,Weaver,1008795600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1071.png +72,1072,Morris,Hall,407019600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1072.png +73,1073,Myrtle,Ferro,840830400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1073.png +74,1074,Gisela,Patterson,464990400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1074.png +75,1075,Stacey,Bishop,493848000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1075.png +76,1076,Ray,Goins,933451200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1076.png +77,1077,Blake,Dickerson,508107600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1077.png +78,1078,David,May,601074000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1078.png +79,1079,Cindy,Wilcox,1021060800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1079.png +80,1080,Mary,Nelson,518644800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1080.png +81,1081,Amy,Smith,785710800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1081.png +82,1082,Joseph,Denton,463089600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1082.png +83,1083,Keith,Wiggin,461707200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1083.png +84,1084,Jody,Hochmuth,752446800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1084.png +85,1085,Beverly,Livesey,739224000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1085.png +86,1086,Nicole,Pharr,884552400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1086.png +87,1087,Aaron,Fox,1090094400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1087.png +88,1088,Rachel,Robinson,528148800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1088.png +89,1089,Leah,Costales,1072472400000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1089.png +90,1090,Thomas,Williams,946501200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1090.png +91,1091,Opal,Morse,463780800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1091.png +92,1092,Alan,Mcgraw,469054800000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1092.png +93,1093,Aaron,Towe,877809600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1093.png +94,1094,Cecil,Struck,416437200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1094.png +95,1095,Corey,Davis,1054411200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1095.png +96,1096,James,Peacock,503442000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1096.png +97,1097,John,Bausch,1013029200000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1097.png +98,1098,Maria,Horton,702504000000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1098.png +99,1099,Samuel,Ladner,815259600000,https://raw.githubusercontent.com/provectus/internship/main/dataeng/02-src-data/1099.png