Day 5

Author: DarkCellar

days/04-06-collections/collections.ipynb

@@ -30,11 +30,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2023-11-15T16:02:04.068436300Z",
-     "start_time": "2023-11-15T16:02:04.053114200Z"
+     "end_time": "2023-11-17T01:06:31.770445700Z",
+     "start_time": "2023-11-17T01:06:31.745630600Z"
     }
    },
    "outputs": [],
@@ -600,16 +600,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-17T01:06:46.790591300Z",
+     "start_time": "2023-11-17T01:06:46.289664200Z"
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "('movies.csv', <http.client.HTTPMessage at 0x10fee00f0>)"
-      ]
+      "text/plain": "('movies.csv', <http.client.HTTPMessage at 0x264400ceba0>)"
      },
-     "execution_count": 21,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -629,8 +632,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-17T01:07:09.958624300Z",
+     "start_time": "2023-11-17T01:07:09.910768Z"
+    }
+   },
    "outputs": [],
    "source": [
     "Movie = namedtuple('Movie', 'title year score')"
@@ -645,8 +653,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-17T01:09:29.726516600Z",
+     "start_time": "2023-11-17T01:09:29.724008300Z"
+    }
+   },
    "outputs": [],
    "source": [
     "def get_movies_by_director(data=movies_csv):\n",
@@ -671,8 +684,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-17T01:09:47.390147900Z",
+     "start_time": "2023-11-17T01:09:47.326915600Z"
+    }
+   },
    "outputs": [],
    "source": [
     "directors = get_movies_by_director()"
@@ -687,23 +705,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-17T01:10:09.726082200Z",
+     "start_time": "2023-11-17T01:10:09.703105300Z"
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "[Movie(title='The Dark Knight Rises', year=2012, score=8.5),\n",
-       " Movie(title='The Dark Knight', year=2008, score=9.0),\n",
-       " Movie(title='Interstellar', year=2014, score=8.6),\n",
-       " Movie(title='Inception', year=2010, score=8.8),\n",
-       " Movie(title='Batman Begins', year=2005, score=8.3),\n",
-       " Movie(title='Insomnia', year=2002, score=7.2),\n",
-       " Movie(title='The Prestige', year=2006, score=8.5),\n",
-       " Movie(title='Memento', year=2000, score=8.5)]"
-      ]
+      "text/plain": "[Movie(title='The Dark Knight Rises', year=2012, score=8.5),\n Movie(title='The Dark Knight', year=2008, score=9.0),\n Movie(title='Interstellar', year=2014, score=8.6),\n Movie(title='Inception', year=2010, score=8.8),\n Movie(title='Batman Begins', year=2005, score=8.3),\n Movie(title='Insomnia', year=2002, score=7.2),\n Movie(title='The Prestige', year=2006, score=8.5),\n Movie(title='Memento', year=2000, score=8.5)]"
      },
-     "execution_count": 25,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -725,20 +739,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-17T01:11:18.955661900Z",
+     "start_time": "2023-11-17T01:11:18.939176400Z"
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "[('Steven Spielberg', 26),\n",
-       " ('Woody Allen', 22),\n",
-       " ('Martin Scorsese', 20),\n",
-       " ('Clint Eastwood', 20),\n",
-       " ('Ridley Scott', 17)]"
-      ]
+      "text/plain": "[('Steven Spielberg', 26),\n ('Woody Allen', 22),\n ('Martin Scorsese', 20),\n ('Clint Eastwood', 20),\n ('Ridley Scott', 17)]"
      },
-     "execution_count": 26,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }

days/04-06-collections/movie_playground.py

@@ -0,0 +1,47 @@
+from collections import defaultdict, namedtuple, Counter, deque
+import csv
+import random
+from urllib.request import urlretrieve
+import os
+
+Movie = namedtuple('Movie', 'title year score gross')
+movies_csv = os.path.join(".\\", "movies.csv")
+
+def main():
+    #movie_data = 'https://raw.githubusercontent.com/pybites/challenges/solutions/13/movie_metadata.csv'
+    #urlretrieve(movie_data, movies_csv)
+
+    directors = get_movies_by_director(movies_csv)
+
+    cnt = Counter()
+    #print(directors.items())
+    for director, movies in directors.items():
+        cnt[director] += len(movies)
+
+    print(cnt.most_common(5))
+
+
+def get_movies_by_director(data):
+    """Extracts all movies from csv and stores them in a dictionary
+       where keys are directors, and values is a list of movies (named tuples)"""
+    directors = defaultdict(list)
+    with open(data, encoding='utf-8') as f:
+        for line in csv.DictReader(f):
+            try:
+                director = line['director_name']
+                movie = line['movie_title'].replace('\xa0', '')
+                year = int(line['title_year'])
+                score = float(line['imdb_score'])
+                gross = float(line['gross'])
+            except ValueError:
+                continue
+
+            m = Movie(title=movie, year=year, score=score, gross=gross)
+            if m.year >= 1960:
+                directors[director].append(m)
+
+    return directors
+
+
+if __name__ == "__main__":
+    main()