一.数据分析的步骤:
1.查看数据并提出问题
2.数据清洗
3.代码编写,提取出结果数据,并分析是否有异常数据,修改代码
4.根据数据选择合适的图表进行展示
5.根据图表小组讨论交流获得最终的结果
二.环境与原始数据准备
安装Anaconda2版本,同时更新软件包更新最新版本 conda upgrade --all
下载first.zip文件,解压
里面有3张csv文件分别是enrollments.csv,daily_engagements.csv,project_submission.csv和一个ipython的notebook
启动cmd 切换到解压之后的文件 输入 jupyter notebook 启动ipython笔记本
三.分析数据
1.从csv加载数据
import unicodecsv
def readcsv(filename):
with open(filename,'rb') as f:
#以字典的形式存放每一行数据
reader = unicodecsv.DictReader(f)
return list(reader)
## 从 daily_engagement.csv 和 project_submissions.csv 载入数据并存
## 储至下面的变量中,然后检查每张表的第1行。
daily_engagement = readcsv('daily-engagement.csv')
project_submissions = readcsv('project-submissions.csv')
enrollments = readcsv('enrollments.csv')
print daily_engagement[0]
print project_submissions[0]
print enrollments[0]
2.修正数据类型
from datetime import datetime as dt
# 将字符串格式的时间转为 Python datetime 类型的时间。
# 如果没有时间字符串传入,返回 None
def parse_date(date):
if date == '':
return None
else:
return dt.strptime(date, '%Y-%m-%d')
# 将可能是空字符串或字符串类型的数据转为 整型 或 None。
def parse_maybe_int(i):
if i == '':
return None
else:
return int(i)
# 清理 enrollments 表格中的数据类型(取消的日期,参加日期,退出的天数,是否取消,是否是Udacity测试账号)
for enrollment in enrollments:
enrollment['cancel_date'] = parse_date(enrollment['cancel_date'])
enrollment['join_date'] = parse_date(enrollment['join_date'])
enrollment['days_to_cancel'] = parse_maybe_int(enrollment['days_to_cancel'])
enrollment['is_canceled'] = enrollment['is_canceled'] == 'True'
enrollment['is_udacity'] = enrollment['is_udacity'] == 'True'
enrollments[0]
# 清理 engagement 的数据类型(时间,课程数量,课程完成数量,项目完成情况,共花费多少时间)
for engagement_record in daily_engagement:
engagement_record['utc_date'] = parse_date(engagement_record['utc_date'])
engagement_record['num_courses_visited'] = int(float(engagement_record['num_courses_visited']))
engagement_record['lessons_completed'] = int(float(engagement_record['lessons_completed']))
engagement_record['projects_completed'] = int(float(engagement_record['projects_completed']))
engagement_record['total_minutes_visited'] = float(engagement_record['total_minutes_visited'])
daily_engagement[0]
# 清理 submissions 的数据类型(项目创建的时间,完成的时间)
for submission in project_submissions:
submission['creation_date'] = parse_date(submission['creation_date'])
submission['completion_date'] = parse_date(submission['completion_date'])
project_submissions[0]
3.修改数据中的格式问题
## 将 daily_engagement 表中的 "acct" 重命名为 ”account_key"
for engagement_record in daily_engagement:
engagement_record['account_key'] = engagement_record['acct']
del [engagement_record['acct']]
4.探索数据
## 计算每张表中的总行数,和独立学生(拥有独立的 account keys)的数量
def unique_student_data(data):
unique_data = set()
for data_point in data:
unique_data.add(data_point['account_key'])
return unique_data
len(enrollments)
unique_enrolled_students = unique_student_data(enrollments)
len(unique_enrolled_students)
len(daily_engagement)
unique_daily_engagement = unique_student_data(daily_engagement)
len(unique_daily_engagement)
len(project_submissions)
unique_project_submissions = unique_student_data(project_submissions)
len(unique_project_submissions)
5.找出问题数据
## 计算出有问题的数据点条数(在 enrollments 中存在,但在 engagement 表中缺失)
num_problem_students = 0
for enrollment in enrollments:
if enrollment['account_key'] not in unique_daily_engagement and enrollment['join_date'] != enrollment['cancel_date']:
num_problem_students +=1
print enrollment
print num_problem_students
6.追踪剩余的问题(移除数据集的测试账号)
# 为所有 Udacity 测试帐号建立一组 set
udacity_test_account = set()
for enrollment in enrollments:
if enrollment['is_udacity']:
udacity_test_account.add(enrollment['account_key'])
len(udacity_test_account)
# 通过 account_key 删除所有 Udacity 的测试帐号
def remove_udacity_account(data):
non_udacity_data = []
for data_point in data:
if data_point['account_key'] not in udacity_test_account:
non_udacity_data.append(data_point)
return non_udacity_data
# 从3张表中移除所有 Udacity 的测试帐号
non_udacity_enrollments = remove_udacity_account(enrollments)
non_udacity_engagement = remove_udacity_account(daily_engagement)
non_udacity_submissions = remove_udacity_account(project_submissions)
#创建一个叫 paid_students 的字典,并在字典中存储所有还没有取消或者注册时间超过7天的学生
paid_students = {}
for enrollment in non_udacity_enrollments:
#如果没有取消并且退课的期限已经超过,就记录学生的key和报名时间
if not enrollment['is_canceled'] or enrollment['days_to_cancel'] > 7:
account_key = enrollment['account_key']
enrollment_date = enrollment['join_date']
#如果account_key不在已缴费的记录中,则将学生记录添加进paid_student中
if account_key not in paid_students or enrollment_date > paid_students[account_key]:
paid_students[account_key] = enrollment_date
len(paid_students)#获取了所有已入学的学生记录
7.获取第一周就已经付费报名的学生
#计算时间差,一周以内,按天计算
def within_one_week(join_date ,engagement_date):
time_delta = join_date - enrollment_date
return time_delta.days >= 0 and time_delta.days < 7
#存放已报名的用户
def remove_free_trial_cancels(data):
new_data = []
for data_point in data:
if data_point['account_key'] in paid_students:
new_data.append(data_point)
return new_data
paid_enrollment = remove_free_trial_cancels(non_udacity_enrollments)
paid_engagement = remove_free_trial_cancels(non_udacity_engagement)
paid_project_missions = remove_free_trial_cancels(non_udacity_submissions)
print len(paid_enrollment)
print len(paid_engagement)
print len(paid_project_missions)
## 创建一个 engagement 记录的列表,该列表只包括付费学生以及加入的前7天的学生的记录
## 输入符合要求的行数
paid_engagement_in_first_week = []
for engagement_record in paid_engagement:
join_date = paid_students[engagement_record['account_key']]
engagement_record_date = engagement_record['utc_date']
if within_one_week(join_date,engagement_record_date):
paid_engagement_in_first_week.append(engagement_record)
len(paid_engagement_in_first_week)
from collections import defaultdict
import numpy as np
#创建基于 student 对 engagement 进行分组的字典,字典的键为帐号(account key),值为包含互动记录的列表
def group_data(data,key_name):
grouped_data = defaultdict(list)
for data_point in data:
key = data_point[key_name]
grouped_data[key].append(data_point)
return grouped_data
# 创建一个包含学生在第1周在教室所花总时间和字典。键为帐号(account key),值为数字(所花总时间)
def sum_grouped_items(grouped_data,field_name):
sumed_data = {}
for key,data_points in grouped_data.items():
total = 0
for data_point in data_points:
total += data_point[field_name]
sumed_data[key] = total
return sumed_data
# 汇总和描述关于教室所花时间的数据
def describe_data(data):
print 'Mean:', np.mean(data)
print 'Standard deviation:', np.std(data)
print 'Minimum:', np.min(data)
print 'Maximum:', np.max(data)
8.获取学习时间最长的学生和时间
total_minutes_by_account = sum_grouped_items(engagement_by_account,'total_minutes_visited')
student_with_max_minutes = None
max_minutes = 0
for student,total_nums in total_minutes_by_account.items():
if total_nums > max_minutes:
max_minutes = total_nums
student_with_max_minutes = student
print max_minutes
for engagement_record in paid_engagement_in_first_week:
if engagement_record['account_key'] == student:
print engagement_record
9.找出第一周的访问数
## 找出第1周学生访问教室天数的平均值、标准差、最小值、最大值。
for engagement_record in paid_engagement:
if engagement_record['num_courses_visited'] > 0:
engagement_record['has_visited'] = 1
else:
engagement_record['has_visited'] = 0
days_visited_by_account = sum_grouped_items(engagement_by_account,'has_visited')
describe_data(days_visited_by_account.values())
10.区分项目通过的学生
## 创建两个付费学生第1周的互动数据列表(engagement)。第1个包含通过项目的学生,第2个包含没通过项目的学生。
subway_project_lesson_keys = ['746169184', '3176718735']
#定义存放通过项目的学员的key
pass_subway_project = set()
for submission in paid_project_missions:
project = submission['lesson_key']
rating = submission['assigned_rating']
#如果等级是passed和distinction加入到pass_subway_project集合中
if project in subway_project_lesson_keys and (rating == 'PASSED' or rating == 'DISTINCTION'):
pass_subway_project.add(submission['account_key'])
passing_engagement = [] #存放通过项目的学生
non_passing_engagement =[] #存放没有通过项目的学生
for engagement_record in paid_engagement_in_first_week:
if engagement_record['account_key'] in pass_subway_project:
passing_engagement.append(engagement_record)
else:
non_passing_engagement.append(engagement_record)
print len(passing_engagement)
print len(non_passing_engagement)
11.对比两组学生的数据
## 计算你所感兴趣的数据指标,并分析通过项目和没有通过项目的两组学生有何异同。
## 你可以从我们之前使用过的数据指标开始(教室的访问时间、课程完成数、访问天数)。
passing_engagement_by_account = group_data(passing_engagement,'account_key')
non_passing_engagement_by_account = group_data(non_passing_engagement,'account_key')
print 'non-passing students'
non_passing_minute = sum_grouped_items(non_passing_engagement_by_account,'total_minutes_visited')
describe_data(non_passing_minute.values())
print 'passing students'
passing_minute = sum_grouped_items(passing_engagement_by_account,'total_minutes_visited')
describe_data(passing_minute.values())
print 'non-passing lessons'
non_passing_lessons = sum_grouped_items(non_passing_engagement_by_account,'lessons_completed')
describe_data(non_passing_lessons.values())
print 'passing lessons'
passing_lessons = sum_grouped_items(passing_engagement_by_account,'lessons_completed')
describe_data(passing_lessons.values())
print 'non-passing visited'
non_passing_visited = sum_grouped_items(non_passing_engagement_by_account,'has_visited')
describe_data(non_passing_visited.values())
print 'passing visited'
passing_visited = sum_grouped_items(passing_engagement_by_account,'has_visited')
describe_data(passing_visited.values())
12.绘制直方图
%pylab inline
import matplotlib.pyplot as plt
import numpy as np
def describe_data(data):
print 'Mean:', np.mean(data)
print 'Standard deviation:', np.std(data)
print 'Minimum:', np.min(data)
print 'Maximum:', np.max(data)
plt.hist(data)
describe_data(passing_minute.values())
describe_data(non_passing_minute.values())
13.改进图表并分析
## 至少改进一幅之前的可视化图表,尝试导入 seaborn 库使你的图表看起来更美观。
## 加入轴标签及表头,并修改一个或多个 hist() 内的变量。
%pylab inline
import seaborn as sns
sns.set(color_codes=True)
plt.hist(non_passing_minute.values(),bins=8)
plt.xlabel('mean of minut')
plt.title('Distribution of classroom visits in the first week ' +
'for students who do not pass the subway project')
plt.hist(passing_minute.values(),bins=8)
plt.xlabel('mean of minut')
plt.title('Distribution of classroom visits in the first week ' +
'for students who do not pass the subway project')