timo-boehm

# load the autoreload extension
%load_ext autoreload
# Set extension to reload modules every time before executing code
%autoreload 2

from helperfunctions import complicated_function_to_return_a_number

complicated_function_to_return_a_number()
# Output: 123

timo-boehm

from numpy.random import randint
import matplotlib.pyplot as plt

# Sample 1000 random values to create a scatterplot
x = randint(low=1, high=1000, size=100)
y = randint(low=1, high=1000, size=100)

# This will show nothing in a Jupyter Notebook
plt.scatter(x, y)
plt.show()

timo-boehm

# Easy to read version
%system date

# Shorthand with "!!" instead of "%system" works equally well
!!date

timo-boehm

import numpy as np
from numpy.random import randint

# A function to simulate one million dice throws.
def one_million_dice():
    return randint(low=1, high=7, size=1000000)

# Let's try %time first
%time throws = one_million_dice()
%time mean = np.mean(throws)

timo-boehm

# Outputs a list of all interactive variables in your environment
%who_ls

# Reduces the output to interactive variables of type "function"
%who_ls function

timo-boehm

import pandas as pd

df = pd.read_csv(path, encoding="ISO-8859-1", usecols=["imdbId", "Title", "Genre", "Poster"])
df.set_index(["imdbId"], inplace=True)
df.dropna(inplace=True)
df.drop_duplicates(subset="Poster", keep=False, inplace=True)

timo-boehm

import re

re_year = re.compile("\((\d{4})\)")
df["year"] = df.Title.map(lambda x: int(re_year.findall(x)[0]) if re_year.findall(x) else None)

timo-boehm

df["Genre"] = df.Genre.map(lambda x: x.split("|"))
all_genres = set([item for l in df.Genre for item in l])
for genre in all_genres:
    new_var = "is_" + re.sub(r'\W+', '', genre.lower())
    df[new_var] = df.Genre.map(lambda x: genre in x)
df.drop(["Genre"], axis=1, inplace=True)

timo-boehm

df_range["decade"] = df_range.year.apply(lambda x: str(int(x))[2] +"0s")
print(f"Movies per decade in the dataset:\n{df_range.decade.value_counts()}\n")

# Outputs:
# 10s    1381
# 00s    1327
# 90s     855
# 80s     582
# 70s     469

timo-boehm

min_number = np.min(df.decade.value_counts())
df_sample = df.groupby("decade").apply(lambda x: x.sample(min_number))