[ckoziak@web415 mvp_landing]$easy_install south
Searching for south
Best match: South 0.8.1
Processing South-0.8.1-py2.4.egg
South 0.8.1 is already the active version in easy-install.pth

Using /home/ckoziak/lib/python2.4/South-0.8.1-py2.4.egg
Processing dependencies for south
Finished processing dependencies for south

[ckoziak@web415 mvp_landing]$ls
join  manage.py  mvp_landing  static
[ckoziak@web415 mvp_landing]$pip install south
Traceback (most recent call last):
File "/home/ckoziak/bin/pip",line 7,in ?
sys.exit(
File "/usr/local/lib/python2.4/site-packages/pkg_resources.py",line 277,in       load_entry_point
return get_distribution(dist).load_entry_point(group,name)
File "/usr/local/lib/python2.4/site-packages/pkg_resources.py",line 2180,in load_entry_point
return ep.load()
File "/usr/local/lib/python2.4/site-packages/pkg_resources.py",line 1913,in load
entry = __import__(self.module_name,globals(),[''__name__''])
File "/home/ckoziak/lib/python2.4/pip-1.4-py2.4.egg/pip/__init__.py",line 10,in ?
from pip.util import get_installed_distributions,get_prog
File "/home/ckoziak/lib/python2.4/pip-1.4-py2.4.egg/pip/util.py",line 17,in ?
from pip.vendor.distlib import version
File "/home/ckoziak/lib/python2.4/pip-1.4-py2.4.egg/pip/vendor/__init__.py",line 8
from __future__ import absolute_import
SyntaxError: from __future__ imports must occur at the beginning of the file

from .base import *

try:
    from .local import *
except:
    pass

try:
    from .live import *
except:
    pass

MEDIA_ROOT = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))),"static","media")

STATIC_ROOT =  os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))),"static-only")

STATICFILES_Dirs = (
    os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))),"static"),)

TEMPLATE_Dirs = (
    os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))),"templates"),)
INSTALLED_APPS = (
''django.contrib.auth'',''django.contrib.contenttypes'',''django.contrib.sessions'',''django.contrib.sites'',''django.contrib.messages'',''django.contrib.staticfiles'',# Uncomment the next line to enable the admin:
''django.contrib.admin'',# Uncomment the next line to enable admin documentation:
''django.contrib.admindocs'',''south'',''join'',)

MEDIA_ROOT = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))),)

INSTALLED_APPS = (
    ''django.contrib.auth'',# Uncomment the next line to enable the admin:
    ''django.contrib.admin'',# Uncomment the next line to enable admin documentation:
    ''django.contrib.admindocs'',)

解决方法

Traceback (most recent call last):
      File "manage.py",line 9,in <module>
        execute_from_command_line(sys.argv)
      File "/usr/local/lib/python2.6/dist-packages/django/core/management/__init__.py",line 422,in execute_from_command_line
        utility.execute()
      File "/usr/local/lib/python2.6/dist-packages/django/core/management/__init__.py",line 361,in execute
        self.fetch_command(subcommand).run_from_argv(self.argv)
      File "/usr/local/lib/python2.6/dist-packages/django/core/management/base.py",line 191,in run_from_argv
        self.execute(*args,**options.__dict__)
      File "/usr/local/lib/python2.6/dist-packages/django/core/management/base.py",line 222,in execute
        output = self.handle(*args,**options)
      File "/usr/local/lib/python2.6/dist-packages/django/core/management/base.py",line 355,in handle
        return self.handle_noargs(**options)
      File "/usr/local/lib/python2.6/dist-packages/django/core/management/commands/shell.py",line 46,in handle_noargs
        from django.db.models.loading import get_models
      File "/usr/local/lib/python2.6/dist-packages/django/db/__init__.py",line 27,in <module>
        connection = connections[DEFAULT_DB_ALIAS]
      File "/usr/local/lib/python2.6/dist-packages/django/db/utils.py",line 81,in __getitem__
        backend = load_backend(db['ENGINE'])
      File "/usr/local/lib/python2.6/dist-packages/django/db/utils.py",line 23,in load_backend
        return import_module('.base',backend_name)
      File "/usr/local/lib/python2.6/dist-packages/django/utils/importlib.py",line 35,in import_module
        __import__(name)
    ImportError: No module named base

解决方法

'ENGINE': 'sqlite3',

'ENGINE': 'django.db.backends.sqlite3',

pandas在Python程序中导入时收到以下错误

monas-mbp:book mona$ sudo pip install python-dateutil
Requirement already satisfied (use --upgrade to upgrade): python-dateutil in /System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python
Cleaning up...
monas-mbp:book mona$ python t1.py
No module named dateutil.parser
Traceback (most recent call last):
  File "t1.py",line 4,in <module>
    import pandas as pd
  File "/Library/Python/2.7/site-packages/pandas/__init__.py",line 6,in <module>
    from . import hashtable,tslib,lib
  File "tslib.pyx",line 31,in init pandas.tslib (pandas/tslib.c:48782)
ImportError: No module named dateutil.parser

还有这里的程序：

import codecs 
from math import sqrt
import numpy as np
import pandas as pd

users = {"Angelica": {"Blues Traveler": 3.5,"Broken Bells": 2.0,"Norah Jones": 4.5,"Phoenix": 5.0,"Slightly Stoopid": 1.5,"The Strokes": 2.5,"Vampire Weekend": 2.0},"Bill":{"Blues Traveler": 2.0,"Broken Bells": 3.5,"Deadmau5": 4.0,"Phoenix": 2.0,"Slightly Stoopid": 3.5,"Vampire Weekend": 3.0},"Chan": {"Blues Traveler": 5.0,"Broken Bells": 1.0,"Deadmau5": 1.0,"Norah Jones": 3.0,"Phoenix": 5,"Slightly Stoopid": 1.0},"Dan": {"Blues Traveler": 3.0,"Broken Bells": 4.0,"Deadmau5": 4.5,"Phoenix": 3.0,"Slightly Stoopid": 4.5,"The Strokes": 4.0,"Hailey": {"Broken Bells": 4.0,"Norah Jones": 4.0,"Vampire Weekend": 1.0},"Jordyn":  {"Broken Bells": 4.5,"Norah Jones": 5.0,"Vampire Weekend": 4.0},"Sam": {"Blues Traveler": 5.0,"Slightly Stoopid": 4.0,"The Strokes": 5.0},"Veronica": {"Blues Traveler": 3.0,"Phoenix": 4.0,"Slightly Stoopid": 2.5,"The Strokes": 3.0}
        }



class recommender:

    def __init__(self,data,k=1,metric='pearson',n=5):
        """ initialize recommender
        currently,if data is dictionary the recommender is initialized
        to it.
        For all other data types of data,no initialization occurs
        k is the k value for k nearest neighbor
        metric is which distance formula to use
        n is the maximum number of recommendations to make"""
        self.k = k
        self.n = n
        self.username2id = {}
        self.userid2name = {}
        self.productid2name = {}
        # for some reason I want to save the name of the metric
        self.metric = metric
        if self.metric == 'pearson':
            self.fn = self.pearson
        #
        # if data is dictionary set recommender data to it
        #
        if type(data).__name__ == 'dict':
            self.data = data

    def convertProductID2name(self,id):
        """Given product id number return product name"""
        if id in self.productid2name:
            return self.productid2name[id]
        else:
            return id


    def userRatings(self,id,n):
        """Return n top ratings for user with id"""
        print ("Ratings for " + self.userid2name[id])
        ratings = self.data[id]
        print(len(ratings))
        ratings = list(ratings.items())
        ratings = [(self.convertProductID2name(k),v)
                   for (k,v) in ratings]
        # finally sort and return
        ratings.sort(key=lambda artistTuple: artistTuple[1],reverse = True)
        ratings = ratings[:n]
        for rating in ratings:
            print("%s\t%i" % (rating[0],rating[1]))




    def loadBookDB(self,path=''):
        """loads the BX book dataset. Path is where the BX files are
        located"""
        self.data = {}
        i = 0
        #
        # First load book ratings into self.data
        #
        f = codecs.open(path + "BX-Book-Ratings.csv",'r','utf8')
        for line in f:
            i += 1
            #separate line into fields
            fields = line.split(';')
            user = fields[0].strip('"')
            book = fields[1].strip('"')
            rating = int(fields[2].strip().strip('"'))
            if user in self.data:
                currentRatings = self.data[user]
            else:
                currentRatings = {}
            currentRatings[book] = rating
            self.data[user] = currentRatings
        f.close()
        #
        # Now load books into self.productid2name
        # Books contains isbn,title,and author among other fields
        #
        f = codecs.open(path + "BX-Books.csv",'utf8')
        for line in f:
            i += 1
            #separate line into fields
            fields = line.split(';')
            isbn = fields[0].strip('"')
            title = fields[1].strip('"')
            author = fields[2].strip().strip('"')
            title = title + ' by ' + author
            self.productid2name[isbn] = title
        f.close()
        #
        #  Now load user info into both self.userid2name and
        #  self.username2id
        #
        f = codecs.open(path + "BX-Users.csv",'utf8')
        for line in f:
            i += 1
            #print(line)
            #separate line into fields
            fields = line.split(';')
            userid = fields[0].strip('"')
            location = fields[1].strip('"')
            if len(fields) > 3:
                age = fields[2].strip().strip('"')
            else:
                age = 'NULL'
            if age != 'NULL':
                value = location + '  (age: ' + age + ')'
            else:
                value = location
            self.userid2name[userid] = value
            self.username2id[location] = userid
        f.close()
        print(i)


    def pearson(self,rating1,rating2):
        sum_xy = 0
        sum_x = 0
        sum_y = 0
        sum_x2 = 0
        sum_y2 = 0
        n = 0
        for key in rating1:
            if key in rating2:
                n += 1
                x = rating1[key]
                y = rating2[key]
                sum_xy += x * y
                sum_x += x
                sum_y += y
                sum_x2 += pow(x,2)
                sum_y2 += pow(y,2)
        if n == 0:
            return 0
        # now compute denominator
        denominator = (sqrt(sum_x2 - pow(sum_x,2) / n)
                       * sqrt(sum_y2 - pow(sum_y,2) / n))
        if denominator == 0:
            return 0
        else:
            return (sum_xy - (sum_x * sum_y) / n) / denominator


    def computeNearestNeighbor(self,username):
        """creates a sorted list of users based on their distance to
        username"""
        distances = []
        for instance in self.data:
            if instance != username:
                distance = self.fn(self.data[username],self.data[instance])
                distances.append((instance,distance))
        # sort based on distance -- closest first
        distances.sort(key=lambda artistTuple: artistTuple[1],reverse=True)
        return distances

    def recommend(self,user):
       """Give list of recommendations"""
       recommendations = {}
       # first get list of users  ordered by nearness
       nearest = self.computeNearestNeighbor(user)
       #
       # now get the ratings for the user
       #
       userRatings = self.data[user]
       #
       # determine the total distance
       totalDistance = 0.0
       for i in range(self.k):
          totalDistance += nearest[i][1]
       # now iterate through the k nearest neighbors
       # accumulating their ratings
       for i in range(self.k):
          # compute slice of pie 
          weight = nearest[i][1] / totalDistance
          # get the name of the person
          name = nearest[i][0]
          # get the ratings for this person
          neighborRatings = self.data[name]
          # get the name of the person
          # now find bands neighbor rated that user didn't
          for artist in neighborRatings:
             if not artist in userRatings:
                if artist not in recommendations:
                   recommendations[artist] = (neighborRatings[artist]
                                              * weight)
                else:
                   recommendations[artist] = (recommendations[artist]
                                              + neighborRatings[artist]
                                              * weight)
       # now make list from dictionary
       recommendations = list(recommendations.items())
       recommendations = [(self.convertProductID2name(k),v)
                          for (k,v) in recommendations]
       # finally sort and return
       recommendations.sort(key=lambda artistTuple: artistTuple[1],reverse = True)
       # Return the first n items
       return recommendations[:self.n]

r = recommender(users)
# The author implementation
r.loadBookDB('/Users/mona/Downloads/BX-Dump/')

ratings = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Book-Ratings.csv',sep=";",quotechar="\"",escapechar="\\")
books = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Books.csv',escapechar="\\")
users = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Users.csv',escapechar="\\")



pivot_rating = ratings.pivot(index='User-ID',columns='ISBN',values='Book-Rating')