Ferdig med oppgavesett 1

uke1/4:population.py

@@ -1,31 +1,30 @@
 def table(data, head):
-    # data er en liste av lister med tre elementer
+    # Formats the data into a nice table in a string
-    t = "{:^30}|{:^25}|{:^10}|\n".format(head[0],head[1],head[2])
+    t = "{:^25}|{:^10}|\n".format(head[0],head[1])
     t += ("-"*len(t)+"\n")
-    for k in data:
+    for n,p in data.items():
-        t += ("{:^30}|{:^25}|{:^10}|\n".format(k[0],k[1], k[2]))
+        t += ("{:^25}|{:^10}|\n".format(n, p))
     return(t)
 
-def population(l):
-    return l[2]
-
 def main():
     with open('norway_municipalities_2017.csv') as f:
-        data = []
+        # we will make a dict where the the kei is the district and the value the population
-        f_iter = iter(f)
+        d = {}
-        # I assume the csv file will always have a heading
+        # assume the csv file always has a header
-        head = f_iter.__next__().strip("\n").split(',')
+        l_iter = iter(f)
-        
+        l_iter.__next__()
-        for l in f:
+        for l in l_iter:
             # we get a list where 0 is the kommune name, 1 is what fylke it is in and 2 is the population
             ll = l.strip("\n").split(',')
-            ll[2] = int(ll[2])
+            name = ll[1]
-            data.append(ll)
+            if name in d.keys():
-
+                d.update({name: d.get(name) + int(ll[2])})
-        data.sort()
+            else:
-
+                d.update({name: int(ll[2])})
-        data.sort(key=population, reverse=True)
+        
-        print(table(data, head))
+        head = ["District", "Population"]
+        res = {key: val for key, val in sorted(d.items(), key = lambda ele: ele[1], reverse=True)}
+        print(table(res, head))
 
 if __name__ == "__main__":
     main()

uke1/5:diagram.py

@@ -0,0 +1,33 @@
+import matplotlib.pyplot as plt
+import numpy as np
+
+def main():
+    with open('norway_municipalities_2017.csv') as f:
+        # we will make a dict where the the kei is the district and the value the population
+        d = {}
+        # assume the csv file always has a header
+        l_iter = iter(f)
+        l_iter.__next__()
+        for l in l_iter:
+            # we get a list where 0 is the kommune name, 1 is what fylke it is in and 2 is the population
+            ll = l.strip("\n").split(',')
+            name = ll[1]
+            if name in d.keys():
+                d.update({name: d.get(name) + int(ll[2])})
+            else:
+                d.update({name: int(ll[2])})
+        
+        head = ["District", "Population"]
+        res = {key: val for key, val in sorted(d.items(), key = lambda ele: ele[1], reverse=True)}
+        
+        n = len(res.keys())
+        x = 0.5 + np.arange(n)
+        y = res.values()
+        fig, ax = plt.subplots()
+        ax.bar(res.keys(), y, edgecolor="white", linewidth=0.7)
+        ax.set(xlabel=head[0], ylabel=head[1])
+        plt.xticks(rotation = 90)
+        plt.show()
+
+if __name__ == "__main__":
+    main()