Assignment writing: Data visualization/Python/Marketing
Budget: $10 – $30 USD
I'm looking for someone who can help with my Marketing Assignment. Im on a module with Data Visualizations/python.
My assignments has the following 15 questions. I have also attached the csv database here:
https://we.tl/t-hHDONbgOsn
Question:
1)in the given dataset drop the type column
2)find the most frequent ratings(in this case ratings are given by the stars column)
3)using data visualisation you've learned in python state 2 pairs with the highest correlations from your graph and the value of the correlations
4)draw histograms showing the distribution of useful reveiws seperated by the stars column
Modelling:
5)drop non-numerical columns(excluding text) this includes date, business id, review id, user id
7)check for missing values and fill columns with apprpriate missing values
8)create a function to process text(ie should remove punctuation marks and also return a list of words in each text)
9)filter your dataset using the stars column and assign the resulting dataset into a new one called final(hint : stars==5|stars==1)
10)using CountVectorizer(specify the above created function as your analyzer) and the decision tree classifier algorithm and any other tool from pythons scikit-learn library build a model to classify text as 1 or 5 star ratings
11)print the classification report and confusion matrix of the model
12)use the model to classify text in rows 5-8
My assignments has the following 15 questions. I have also attached the csv database here:
https://we.tl/t-hHDONbgOsn
Question:
1)in the given dataset drop the type column
2)find the most frequent ratings(in this case ratings are given by the stars column)
3)using data visualisation you've learned in python state 2 pairs with the highest correlations from your graph and the value of the correlations
4)draw histograms showing the distribution of useful reveiws seperated by the stars column
Modelling:
5)drop non-numerical columns(excluding text) this includes date, business id, review id, user id
7)check for missing values and fill columns with apprpriate missing values
8)create a function to process text(ie should remove punctuation marks and also return a list of words in each text)
9)filter your dataset using the stars column and assign the resulting dataset into a new one called final(hint : stars==5|stars==1)
10)using CountVectorizer(specify the above created function as your analyzer) and the decision tree classifier algorithm and any other tool from pythons scikit-learn library build a model to classify text as 1 or 5 star ratings
11)print the classification report and confusion matrix of the model
12)use the model to classify text in rows 5-8