1 of 17

IMDB MOVIE ANALYSIS

By Rajni Rai

2 of 17

Introduction

Here is brief description about IMDB movies project.In this project we need to remove unwanted data in raw dataset for this we have to clean data by dropping columns and removing null values and unwanted rows which are not in use to perform tasks.Major part of this project is to analysis data which is required in finding outputs. For different-different tasks need to create new columns which is required to proceed the process.There is need to plot graphs/pie charts to visualize the data which helps to show results in a proper manner.Dataset having various columns of different-different IMDB movies.We are required to frame the problem.which we want to shed some light on.�We can do this by asking 'What?' This is where we frame the problem i.e. What is the problem?�Use these questions to guide your thinking-�What do you see happening? What is your hypothesis for the cause of the problem?

What is the impact of the problem on stakeholders.

What is the impact of the problem not being solved?

After finding all answers we can define problem easily, there is five whys approach which is also called root cause analysis to define the process we are using this approach in this project to perform the task.

​

​

3 of 17

Task(A)

Cleaning the data: This is one of the most important step to perform before moving forward with the analysis. Use your knowledge learned till now to do this. (Dropping columns, removing null values, etc.)� Task: Clean the data

Insights- In cleaning data firstly I have done data analysis then I found that there are so many null values present I need to remove unwanted values which is holding unnecessary space. I dropped few columns those are not required during task column names -color,duration,director_facebook_likes,actor_3_facebook_likes,actor_2_name,actor_1_facebook_likes,cast_total_facebook_likes,actor_3_name,facenumber_in_poster,plot_keywords,movie_imdb_link,country,content_rating,actor_2_facebook_likes,aspect_ratio,movies_facebook_likes.

I also removed few rows during cleaning data.For cleaning rows I applied filter for all selected columns then select all blanks in each column then screen all common rows which have all blank cells in each single row then select the row and deleted it from the sheet.There are 1152 unwanted rows i have removed which are not in use.Removed null values.After cleaning data there are 3892 rows remains.

​

​

4 of 17

Clean data

5 of 17

Task(B)

Movies with highest profit: Create a new column called profit which contains the difference of the two columns: gross and budget. Sort the column using the profit column as reference. Plot profit (y-axis)vs budget (x- axis) and observe the outliers using the appropriate chart type.

Task: Find the movies with the highest profit?

During this task i created column named profit which has difference between gross and budget value.

Formula- Profit= Gross-Budget

Then Sort the column using the profit column as reference. Plot profit (y-axis)vs budget (x- axis) and observe the outliers using the appropriate chart type.

Insights- Here is data shows highest profit.Plotted a graph between profit and budget.

​

6 of 17

Task(B)

7 of 17

Task(C)

Top 250: Create a new column IMDb_Top_250 and store the top 250 movies with the highest IMDB Rating (corresponding to the column: imdb_score). Also make sure that for all of these movies, the num_voted_users is greater than 25,000. Also add a Rank column containing the values 1 to 250 indicating the ranks of the corresponding films.�Extract all the movies in the IMDb_Top_250 column which are not in the English language and store them in a new column named Top_Foreign_Lang_Film. You can use your own imagination also!� Task: Find IMDB Top 250

Insights -Here is IMDB_Top_250 column which contains Top 250 movies with highest Imbd rating which has the num_voted_user greater than 25000.firstly I use sort to find highest imdb rating then applied number filter on the num_voted_users which should be greater than 25000 then used conditional formatting and filters to remove duplicates. Then created IMDB_Top_250 column and stored all 250 movies.

Extracted foreign language movies from IMDB_Top_250 column from filter which is applied on language column to remove English language.

8 of 17

Task(C)

9 of 17

Task(C)

10 of 17

Task(D)

Best Directors: TGroup the column using the director_name column.�Find out the top 10 directors for whom the mean of imdb_score is the highest and store them in a new column top10director. In case of a tie in IMDB score between two directors,sort them alphabetically.�Task: Find the best directors.

Insights-I grouped all the director_name using pivot table then calculate highest mean of imdb_score,sort them.

Here is link of data sheet-

https://docs.google.com/spreadsheets/d/1Fg1UgxkpTQIumpfGE4CboPdJzJvQ2DqF/edit?usp=sharing&ouid=109642230242261121568&rtpof=true&sd=true

​

​

11 of 17

Task(E)

Popular Genres: Perform this step using the knowledge gained while performing previous steps.

Task: Find popular genres

Insights: I used sort,filtering in excel and using COUNTIF function to find popular genres. Most popular genre is Drama.

Here is link of data sheet-

https://docs.google.com/spreadsheets/d/14Zxb4knpnK1yS5Pka3fXxKMxhzK-bC9z/edit?usp=sharing&ouid=109642230242261121568&rtpof=true&sd=true

​

12 of 17

Task(F)

Charts: Create three new columns namely,Meryl_Streep,Leo_Caprio,and Brad_Pitt which contain the movies in which the actors: 'Meryl Streep', 'Leonardo DiCaprio', and 'Brad Pitt' are the lead actors.Use only the actor_1_name column for extraction.Also, make sure that you use the names 'Meryl Streep', 'Leonardo DiCaprio',and 'Brad Pitt' for the said extraction.�Append the rows of all these columns and store them in a new column named Combined.�Group the combined column using the actor_1_name column.�Find the mean of the num_critic_for_reviews and num_users_for_review and identify the actors which have the highest mean.�Observe the change in number of voted users over decades using a bar chart.Create a column called decade which represents the decade to which every movie belongs to.For example,the title_year year 1923,1925 should be stored as 1920s.Sort the column based on the column decade, group it by decade and find the sum of users voted in each decade. Store this in a new data frame called df_by_decade.�Task: Find the critic-favorite and audience-favorite actors.

​

​

13 of 17

Task(F)

Insights- Here is output given and graph shows decade data. In output the critic-favorite and audience- favorite actors are shown in datasheet which shows result.I used pivot table,graph to visualize decade data.

Most favourite actor is Leonardo Dicaprio for both critic-favourite and audience-favourite.

Here is link of data sheet-

https://docs.google.com/spreadsheets/d/186MvHbG5JqMB3s0Iphddm9fwo6KqIxQd/edit?usp=sharing&ouid=109642230242261121568&rtpof=true&sd=true

​

​

14 of 17

Task(F)

Here is link of data sheet-

15 of 17

Approach

Here we are using five why’s approach to solve all the problems.

It's also called the Root Cause Analysis,developed by Sakichi Toyoda,founder of Toyota Industries.

Once you have the problem better defined, you can use 5 Whys technique to determine its root cause by repeated asking the question “Why”.

Tech-stack used – Microsoft excel 365 online

In this project excel formulas used for find out the results and for visualization of data there are multiple chart type used.

Firstly clean the data by removing unwanted columns and rows then used excel filter to sort the data. Create new columns which contains results then represent it in form of chats/graphs .Pivot table used to group the data then organized it in a proper manner according to question asked in task.

​

.

​

��

16 of 17

Result

In this project i get to know about Pivot table,Graphs how to use them to visualize the data.What is the best way to represent the data in worksheets how to clean data in excel how to apply formulas in excel all I learnt about while I have done this project.Important part of this project is clean the data and arrange in a proper way.

The best thing is about this project is that it covers all kind of topics which are required to become a efficient data analyst.It will definitely help me in future project.I got an idea about what kind of work is provided by companies for a data analyst.

From this project,I got an idea about how as a business or data analyst we work on real-time data to take any data-driven decision.

​

17 of 17

THANK-YOU