updates for 2020 phase 2

anandkumar1990 · Jun 19, 2020 · 046bae0 · 046bae0
1 parent 31f7adf
commit 046bae0
Show file tree

Hide file tree

Showing 11 changed files with 2,227 additions and 157 deletions.
diff --git a/03-Methods and Functions/.ipynb_checkpoints/02-Functions-checkpoint.ipynb b/03-Methods and Functions/.ipynb_checkpoints/02-Functions-checkpoint.ipynb
diff --git a/03-Methods and Functions/02-Functions.ipynb b/03-Methods and Functions/02-Functions.ipynb
diff --git a/08-Milestone Project - 2/00-Milestone-2-Warmup-Project.ipynb b/08-Milestone Project - 2/00-Milestone-2-Warmup-Project.ipynb
@@ -3,7 +3,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }
@@ -24,7 +26,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.4"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,

diff --git a/15-PDFs-and-Spreadsheets/.ipynb_checkpoints/02-PDFs-Spreadsheets-Puzzle-checkpoint.ipynb b/15-PDFs-and-Spreadsheets/.ipynb_checkpoints/02-PDFs-Spreadsheets-Puzzle-checkpoint.ipynb
@@ -24,7 +24,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   },
@@ -45,7 +47,7 @@
     }
    ],
    "source": [
-    "# THe correct result is shown below, if you can't download ffrom Google Drive, \n",
+    "# THe correct result is shown below, if you can't download from Google Drive, \n",
     "# we added the PDF file to the Exercise_Files folder already"
    ]
   },
@@ -59,7 +61,9 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# You should get this phone number\n",
@@ -84,7 +88,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.4"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,

diff --git a/...and-Spreadsheets/.ipynb_checkpoints/03-PDFs-Spreadsheets-Puzzle-Solution-checkpoint.ipynb b/...and-Spreadsheets/.ipynb_checkpoints/03-PDFs-Spreadsheets-Puzzle-Solution-checkpoint.ipynb
@@ -19,6 +19,17 @@
     "## Task One: Grab the Google Drive Link from .csv File"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import csv"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -29,7 +40,9 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "data = open('Exercise_Files/find_the_link.csv',encoding=\"utf-8\")\n",
@@ -54,7 +67,9 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "link_list = []\n",
@@ -92,7 +107,9 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "link_str = ''\n",
@@ -130,7 +147,9 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import PyPDF2"
@@ -139,7 +158,9 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "f = open('Exercise_Files/Find_the_Phone_Number.pdf','rb')"
@@ -148,7 +169,9 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "pdf = PyPDF2.PdfFileReader(f)"
@@ -180,13 +203,76 @@
    "source": [
     "## Phone Number Matching\n",
     "\n",
-    "Lot's of ways to do this, but you had to figure out the phone number was in format ###.###.####"
+    "Lot's of ways to do this, but you had to figure out the phone number was in format ###.###.####\n",
+    "\n",
+    "Hint: https://stackoverflow.com/questions/4697882/how-can-i-find-all-matches-to-a-regular-expression-in-python"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "pattern = r'\\d{3}'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "all_text = ''\n",
+    "\n",
+    "for n in range(pdf.numPages):\n",
+    "    \n",
+    "    page = pdf.getPage(n)\n",
+    "    page_text = page.extractText()\n",
+    "    \n",
+    "    all_text = all_text+' '+page_text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "for match in re.finditer(pattern,all_text):\n",
+    "    print(match)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
    "metadata": {},
+   "source": [
+    "Once you know the correct pattern:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import re"
@@ -195,7 +281,9 @@
   {
    "cell_type": "code",
    "execution_count": 24,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "pattern = r'\\d{3}.\\d{3}.\\d{4}' "
@@ -253,7 +341,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.4"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,

diff --git a/15-PDFs-and-Spreadsheets/00-Working-with-CSV-Files.ipynb b/15-PDFs-and-Spreadsheets/00-Working-with-CSV-Files.ipynb
@@ -54,7 +54,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import csv"
@@ -70,7 +72,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "data = open('example.csv')"
@@ -108,7 +112,9 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "csv_data = csv.reader(data)"
@@ -153,7 +159,9 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "data = open('example.csv',encoding=\"utf-8\")\n",
@@ -255,7 +263,9 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "all_emails = []\n",
@@ -290,7 +300,9 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "full_names = []\n",
@@ -352,7 +364,9 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# newline controls how universal newlines works (it only applies to text\n",
@@ -363,7 +377,9 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "csv_writer = csv.writer(file_to_output,delimiter=',')"
@@ -392,7 +408,9 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "csv_writer.writerows([['1','2','3'],['4','5','6']])"
@@ -401,7 +419,9 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "file_to_output.close()"
@@ -418,7 +438,9 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "f = open('to_save_file.csv','a',newline='')"
@@ -427,7 +449,9 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "csv_writer = csv.writer(f)"
@@ -456,7 +480,9 @@
   {
    "cell_type": "code",
    "execution_count": 23,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "f.close()"
@@ -486,7 +512,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.4"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,