Added resources

Author: xhebraj

hw1/README.md

@@ -0,0 +1,26 @@
+# Data Mining Homework 1
+
+The programs expect to find `beers.txt` under `data/`.
+
+In order to launch the code samples make sure to be in the program's
+directory (i.e. launch the program `p4.sh` from the `p4/` folder)
+
+
+### Problem 6
+
+```
+usage: p6.py [-h] [-f] [-n N_PROC]
+
+Scrape kijiji.it Informatica/Grafica/Web category
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -f, --full_desc       Download full description
+  -n N_PROC, --n_proc N_PROC
+                        Number of processes to run
+```
+
+
+```
+author: Anxhelo Xhebraj <[email protected]>
+```

hw1/data/.gitkeep

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 from collections import Counter
 from random import shuffle
 

hw1/homework1-solution.pdf

@@ -1,3 +1,3 @@
-#! /bin/env bash
+#!/usr/bin/env bash
 
 awk -F '\t' '{arr[$1]++} END{for (a in arr) print arr[a], a}' ../data/beers.txt | sort -n -r | head -n 10 | cut -d' ' -f2-

hw1/homework1.pdf

@@ -1,4 +1,4 @@
-#!/bin/env python3
+#!/usr/bin/env python3
 import heapq
 
 beers = {}

hw1/latex_src/house.png

@@ -1,4 +1,4 @@
-#! /usr/bin/env python3
+#!/usr/bin/env python3
 
 import argparse
 from lxml import html
@@ -76,11 +76,8 @@ def crawl_and_save(prid, urls, get_content, f):
                 n_items += len(content)
                 bad_req = False
             except (Exception, requests.exceptions.ConnectionError):
-                print("p"+str(prid) + ": Entering sleep")
                 time.sleep(60)
-                print("p"+str(prid) + ": Awake")
     f.close()
-    print("p" + str(prid) + ": ", n_items, " Retrieved")
     return n_items