Python數據分析流程

一.數據分析的步驟:

1.查看數據並提出問題

2.數據清洗

3.代碼編寫,提取出結果數據,並分析是否有異常數據,修改代碼

4.根據數據選擇合適的圖表進行展示

5.根據圖表小組討論交流獲得最終的結果

 

二.環境與原始數據准備

安裝Anaconda2版本,同時更新軟件包更新最新版本  conda upgrade --all

下載first.zip文件,解壓

里面有3張csv文件分別是enrollments.csv,daily_engagements.csv,project_submission.csv和一個ipython的notebook

啟動cmd 切換到解壓之后的文件 輸入 jupyter notebook 啟動ipython筆記本

 

三.分析數據

1.從csv加載數據

import unicodecsv


def readcsv(filename):
    with open(filename,'rb') as f:
        #以字典的形式存放每一行數據
        reader = unicodecsv.DictReader(f)
        return list(reader)    

 

## 從 daily_engagement.csv 和 project_submissions.csv 載入數據並存
## 儲至下面的變量中，然后檢查每張表的第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.修正數據類型

from datetime import datetime as dt

# 將字符串格式的時間轉為 Python datetime 類型的時間。
# 如果沒有時間字符串傳入，返回 None
def parse_date(date):
    if date == '':
        return None
    else:
        return dt.strptime(date, '%Y-%m-%d')

    
# 將可能是空字符串或字符串類型的數據轉為 整型 或 None。
def parse_maybe_int(i):
    if i == '':
        return None
    else:
        return int(i)

 

# 清理 enrollments 表格中的數據類型(取消的日期,參加日期,退出的天數,是否取消,是否是Udacity測試賬號)
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 的數據類型(時間,課程數量,課程完成數量,項目完成情況,共花費多少時間)
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 的數據類型(項目創建的時間,完成的時間)
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.修改數據中的格式問題

## 將 daily_engagement 表中的 "acct" 重命名為 ”account_key"
for engagement_record in daily_engagement:
    engagement_record['account_key'] = engagement_record['acct']
    del [engagement_record['acct']]

 4.探索數據

## 計算每張表中的總行數，和獨立學生（擁有獨立的 account keys）的數量
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.找出問題數據

## 計算出有問題的數據點條數（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.追蹤剩余的問題(移除數據集的測試賬號)

# 為所有 Udacity 測試帳號建立一組 set 
udacity_test_account = set()
for enrollment in enrollments:
    if enrollment['is_udacity']:
        udacity_test_account.add(enrollment['account_key'])
len(udacity_test_account)


# 通過 account_key 刪除所有 Udacity 的測試帳號
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

# 從3張表中移除所有 Udacity 的測試帳號
non_udacity_enrollments = remove_udacity_account(enrollments)
non_udacity_engagement = remove_udacity_account(daily_engagement)
non_udacity_submissions = remove_udacity_account(project_submissions)

#創建一個叫 paid_students 的字典，並在字典中存儲所有還沒有取消或者注冊時間超過7天的學生
paid_students = {}
for enrollment in non_udacity_enrollments:
　　#如果沒有取消並且退課的期限已經超過,就記錄學生的key和報名時間
    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不在已繳費的記錄中,則將學生記錄添加進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)#獲取了所有已入學的學生記錄

 7.獲取第一周就已經付費報名的學生

#計算時間差,一周以內,按天計算
def within_one_week(join_date ,engagement_date):
    time_delta = join_date - enrollment_date
    return time_delta.days >= 0 and time_delta.days < 7
    


#存放已報名的用戶
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)

## 創建一個 engagement 記錄的列表，該列表只包括付費學生以及加入的前7天的學生的記錄 
## 輸入符合要求的行數
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
#創建基於 student 對 engagement 進行分組的字典，字典的鍵為帳號（account key），值為包含互動記錄的列表
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

# 創建一個包含學生在第1周在教室所花總時間和字典。鍵為帳號（account key），值為數字（所花總時間）
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

# 匯總和描述關於教室所花時間的數據
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.獲取學習時間最長的學生和時間

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.找出第一周的訪問數

## 找出第1周學生訪問教室天數的平均值、標准差、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.區分項目通過的學生

## 創建兩個付費學生第1周的互動數據列表（engagement）。第1個包含通過項目的學生，第2個包含沒通過項目的學生。

subway_project_lesson_keys = ['746169184', '3176718735']
#定義存放通過項目的學員的key
pass_subway_project = set()
for submission in paid_project_missions:
    project = submission['lesson_key']
    rating = submission['assigned_rating']
　　#如果等級是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 = [] #存放通過項目的學生
non_passing_engagement =[] #存放沒有通過項目的學生

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.對比兩組學生的數據

## 計算你所感興趣的數據指標，並分析通過項目和沒有通過項目的兩組學生有何異同。
## 你可以從我們之前使用過的數據指標開始（教室的訪問時間、課程完成數、訪問天數）。
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.繪制直方圖

%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.改進圖表並分析

## 至少改進一幅之前的可視化圖表，嘗試導入 seaborn 庫使你的圖表看起來更美觀。
## 加入軸標簽及表頭，並修改一個或多個 hist() 內的變量。
%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')