hw1

HW1-data.csv

@@ -0,0 +1,21 @@
+User,"Gender (1 =F, 0=M)",260: Star Wars: Episode IV - A New Hope (1977),1210: Star Wars: Episode VI - Return of the Jedi (1983),356: Forrest Gump (1994),"318: Shawshank Redemption, The (1994)","593: Silence of the Lambs, The (1991)",3578: Gladiator (2000),1: Toy Story (1995),2028: Saving Private Ryan (1998),296: Pulp Fiction (1994),1259: Stand by Me (1986),2396: Shakespeare in Love (1998),2916: Total Recall (1990),780: Independence Day (ID4) (1996),541: Blade Runner (1982),1265: Groundhog Day (1993),"2571: Matrix, The (1999)",527: Schindler's List (1993),"2762: Sixth Sense, The (1999)",1198: Raiders of the Lost Ark (1981),34: Babe (1995)
+755,0,1,5,2,,4,4,2,2,,3,2,,5,2,,4,2,5,,
+5277,0,5,3,,2,4,2,1,,,4,3,2,2,,2,,5,1,3,
+1577,1,,,,5,2,,4,,,1,,1,4,4,1,1,2,3,1,3
+4388,0,,3,,,,1,2,3,4,,,4,1,3,5,,5,1,1,2
+1202,1,4,3,4,1,4,1,,4,,1,5,1,,4,,3,5,5,,
+3823,1,2,4,4,4,,,3,1,4,4,5,2,4,,1,,,3,,2
+5448,0,,,3,1,1,4,,5,2,,1,,,3,,1,,,5,2
+5347,0,4,,,,3,2,2,,3,,,2,3,2,4,,1,3,5,
+4117,1,5,1,,4,2,4,4,4,,1,2,3,1,,5,,,,,5
+2765,0,4,2,,5,3,,4,3,4,,,,2,,,2,5,1,,
+5450,1,2,1,5,,,5,5,,,,,3,2,,,1,,2,1,4
+139,0,3,5,2,,2,,2,,1,,3,,3,,2,5,,,,2
+1940,0,2,3,,5,4,,4,5,,,,2,4,,3,,,,5,
+3118,1,3,,3,,2,,3,,,4,,1,2,2,3,5,1,,,
+4656,1,4,4,,,5,5,2,,3,5,,1,3,,2,,3,,3,1
+4796,1,,,1,,3,2,,2,,1,5,,,,5,2,2,4,3,4
+6037,0,,,,,4,,2,,2,,2,,,,,4,,,,
+3048,1,4,5,1,5,1,1,4,,5,,,,,4,,,2,1,2,5
+4790,0,5,1,,,,4,2,1,3,3,3,1,,,,2,,,,
+4489,0,1,2,2,4,5,,2,3,2,2,1,,,5,5,4,3,5,3,

HW1.py

@@ -0,0 +1,77 @@
+import pandas as pd
+import numpy as np
+import functools
+
+GENDER = "Gender (1 =F, 0=M)"
+TOY_STORY = "1: Toy Story (1995)"
+
+def dbg(v):
+    print(v)
+    return v
+
+def correl(x, y):
+    x = x.dropna()
+    y = y.dropna()
+    xb = x.mean()
+    yb = y.mean()
+    num = sum(map(lambda c: (c[0] - xb) * (c[1] - yb), zip(x, y)))
+    den = np.sqrt(sum(map(lambda x: pow(x - xb, 2), x)) *
+            sum(map(lambda y: pow(y - yb, 2), y)))
+    return num / den
+X = pd.Series([195, 151, 148, 189, 183, 154])
+Y = pd.Series([200, 180, 178, 165, 192, 144])
+print(correl(X, Y))
+assert np.isclose(correl(X, Y), 0.46706598573232)
+
+data = pd.read_csv("HW1-data.csv")
+gender_data = data.iloc[:, :2].to_dict(orient="list")
+users = gender_data["User"]
+gender_data = dict(zip(gender_data["User"], gender_data[GENDER]))
+print(gender_data)
+# print(gender_data)
+
+movie_data = data.iloc[:, 2:]
+# movie_data.columns = movie_data.iloc[0]
+# print(movie_data)
+
+print("Response 1: highest average")
+print(movie_data.mean().sort_values(ascending=False)[:3])
+print()
+
+print("Response 2: popularity (# of reviews)")
+print(movie_data.count().sort_values(ascending=False)[:3])
+print()
+
+print("Response 3: %reviews greater than 4")
+print(movie_data.apply(lambda s: (s >= 4).sum() / s.count()).sort_values(ascending=False)[:3])
+print()
+
+print("Response 4: %correlation with Toy Story")
+toy_story_raters = movie_data.transpose().loc[TOY_STORY]
+toy_story_raters_n = toy_story_raters.notna()
+def toy_story_correlate(s):
+    xy = 0
+    for i, v in s.notna().items():
+        if toy_story_raters_n[i] and v:
+            xy += 1
+    x = toy_story_raters.count()
+    return xy/x
+print(movie_data.apply(toy_story_correlate).sort_values(ascending=False)[:5])
+print()
+
+print("Response 5: correlation with Toy Story")
+def toy_story_correlate2(s):
+    return correl(s, toy_story_raters)
+print(movie_data.apply(toy_story_correlate2).sort_values(ascending=False))
+print("TODO NOT DONE")
+print()
+
+print("Response 6: Mean difference by gender")
+isman = lambda id: not gender_data[id]
+iswoman = lambda id: gender_data[id]
+def gender_rating(g, s):
+    v = pd.Series(map(lambda c: c[1], filter(lambda c: gender_data[users[c[0]]] == g, s.items())))
+    return v.mean()
+men_ratings = movie_data.apply(functools.partial(gender_rating, 0))
+women_ratings = movie_data.apply(functools.partial(gender_rating, 1))
+print(men_ratings, women_ratings)