add docker file and python scripts

Dockerfile

@@ -0,0 +1,16 @@
+FROM ubuntu:latest
+
+RUN apt update && apt install -y python3 && apt install -y nano
+
+RUN apt update && apt install python3-pip -y
+RUN pip3 install kaggle && pip3 install pandas && pip3 install scikit-learn && pip3 install matplotlib
+RUN apt install -y curl
+RUN pip3 install --user wget
+
+WORKDIR /app
+
+COPY ./init.py ./
+COPY ./stats.py ./
+
+RUN mkdir /.kaggle
+RUN chmod -R 777 /.kaggle

init.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn import preprocessing
+import kaggle
+
+kaggle.api.authenticate()
+kaggle.api.dataset_download_files('jilkothari/finance-accounting-courses-udemy-13k-course', path='.', unzip=True)
+
+courses = pd.read_csv('courses.csv')
+
+#Delete redundant columns
+imp_col = ['id', 'title', 'url', 'is_paid', 'num_subscribers', 'rating', 'num_reviews', 'created']
+courses = courses[imp_col]
+courses.to_csv("courses.csv", index=False)
+courses = pd.read_csv('courses.csv')
+
+#Delete empty rows of rating column and number of reviews less than 10
+rating_col = 'rating'
+num_reviews_col = 'num_reviews'
+courses = courses.drop(courses[courses.rating == 0].index)
+courses = courses.drop(courses[courses.num_reviews < 10].index)
+
+#Simplify numbers to one decimal place and format 'title' column to specifc schema
+courses = courses.round(1)
+courses['title'] = courses['title'].str.lower()
+courses['title'] = courses['title'].str.replace(" ", "_")
+
+#Delete artifacts
+courses = courses.dropna()
+
+#Split dataset into 60% 20% 20% - train, valid, test
+courses_train, courses_validate, courses_test = np.split(courses.sample(frac=1), [int(.6*len(courses)), int(.8*len(courses))])
+
+#Create new csv
+courses_train.to_csv("train.csv", index=False)
+courses_validate.to_csv("valid.csv",index=False)
+courses_test.to_csv("test.csv",index=False)

stats.py

@@ -0,0 +1,10 @@
+import pandas as pd
+import pandas as pd
+
+train = pd.read_csv('train.csv')
+test = pd.read_csv('test.csv')
+valid = pd.read_csv('valid.csv')
+
+print("train size: ", train.size)
+print("test size: ", test.size)
+print("valid size: ", valid.size)