Project: Visualizing the History of Nobel Prize Winners

# Loading in required libraries
import pandas as pd
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt

# Start coding here!

# create nobel_data dataframe
nobel_data = pd.read_csv("data/nobel.csv")

# print first rows of nobel_data
print(nobel_data.head())

# columns of nobel_data
print(nobel_data.columns)

# top_country
top_country = nobel_data["birth_country"].value_counts().index[0]
print("The most commonly awarded birth country:", top_country)

# top_gender
top_gender = nobel_data["sex"].value_counts().index[0]
print("The most commonly awarded gender:", top_gender)

# us_born column
nobel_data["us_born"] = False
nobel_data.loc[nobel_data["birth_country"] == "United States of America", "us_born"] = True
print(nobel_data[nobel_data["birth_country"] == "United States of America"][["birth_country", "us_born"]].head())

# decade column
nobel_data["decade"] = (10 * (nobel_data["year"] // 10)).astype(str) + "s"
print(nobel_data.head())
print(nobel_data.tail())

# us_ratio column
nobel_pivot_table = nobel_data.pivot_table(values=["us_born", "year"], index="decade", aggfunc={"us_born": "sum", "year": "count"}).rename(columns={"us_born": "USA winners", "year": "Total winners"})
nobel_pivot_table["us_ratio"] = (nobel_pivot_table["USA winners"] / nobel_pivot_table["Total winners"] * 100).round()
print(nobel_pivot_table.sort_values("us_ratio", ascending=False))

max_decade_usa = int(nobel_pivot_table.sort_values("us_ratio", ascending=False).index[0][:-1])
print("The decade had the highest ratio of US-born Nobel Prize winners to total winners in all categories:", str(max_decade_usa) + "s")

# lineplot => decade and us_ratio
sns.lineplot(x="decade", y="us_ratio", data=nobel_pivot_table, marker="X")
plt.xticks(rotation=90)
plt.ylabel("USA-born winners (%)")
plt.xlabel("Decade")
plt.title("American Nobel Laureates Through the Decades")
plt.show()

# countplot => sex vs decade
sns.countplot(x=nobel_data["sex"], data=nobel_data, hue="decade", order=["Female", "Male"], alpha=0.6)
plt.title("Distribution of Nobel Prize Winners by Gender Over the Decades")
plt.xlabel("Gender")
plt.ylabel("Count of Nobel Prize Winners")
plt.show()

# countplot => category vs decade
sns.catplot(x=nobel_data["category"], data=nobel_data, hue="decade", kind="count", alpha=0.6)
plt.title("Distribution of Nobel Prize Winners by Category Over the Decades")
plt.xlabel("Category")
plt.ylabel("Count of Nobel Prize Winners")
plt.show()

# is_female column
nobel_data["is_female"] = False
nobel_data.loc[nobel_data["sex"] == "Female", "is_female"] = True
print(nobel_data[nobel_data["sex"] == "Female"][["sex", "is_female"]].head())

# female_ratio column
nobel_pivot_table = nobel_data.pivot_table(values=["is_female", "year"], index=["decade", "category"], aggfunc={"is_female": "sum", "year": "count"}).rename(columns={"is_female": "Female winners", "year": "Total winners"}).reset_index()
nobel_pivot_table["female_ratio"] = (nobel_pivot_table["Female winners"] / nobel_pivot_table["Total winners"] * 100).round()
print(nobel_pivot_table.sort_values("female_ratio", ascending=False))

# top decade and category
top_decade_female = int(nobel_pivot_table.sort_values("female_ratio", ascending=False).values[0, 0][:-1])
print("The decade had the highest ratio of female Nobel Prize winners to total winners in all categories:", str(top_decade_female) + "s")

top_category_female = nobel_pivot_table.sort_values("female_ratio", ascending=False).values[0, 1]
print("The category had the highest ratio of female Nobel Prize winners to total winners:", top_category_female)

max_female_dict = {top_decade_female: top_category_female}
print(max_female_dict)

# lineplot => decade and female_ratio
sns.lineplot(x="decade", y="female_ratio", data=nobel_pivot_table, marker="X", hue="category")
plt.xticks(rotation=90)
plt.ylabel("Female winners (%)")
plt.xlabel("Decade")
plt.title("Nobel Prize-Winning Women Across the Decades")
plt.show()

# first_woman
female_winners = nobel_data[nobel_data["sex"] == "Female"]
first_woman_name = female_winners.sort_values("year").head(1).values[0, 7]
print("The first woman to receive a Nobel Prize:", first_woman_name)

# first_woman_category
first_woman_category = female_winners.sort_values("year").head(1).values[0, 1]
print("The category:", first_woman_category)

# ind_pivot and org_pivot columns
ind_pivot = nobel_data.pivot_table(values="year", index="full_name", aggfunc="count")["year"].reset_index()
org_pivot = nobel_data.pivot_table(values="year", index="organization_name", aggfunc="count")["year"].reset_index()

# more than one times
repeat_list = []
print(ind_pivot[ind_pivot["year"] > 1].values[:, 0])

repeat_list += list(ind_pivot[ind_pivot["year"] > 1].values[:, 0])
print(repeat_list)

# us_born (alternative way)
nobel_data["usa_born_winner"] = nobel_data["birth_country"] == "United States of America"
print(nobel_data[["birth_country", "usa_born_winner"]].head())

nobel_data["decade"] = (np.floor(nobel_data["year"] / 10) * 10).astype(int)
print(nobel_data[["year", "decade"]].head())

prop_usa_winners = nobel_data.groupby("decade", as_index=False)["usa_born_winner"].mean()
print(prop_usa_winners.head())

max_decade_usa = prop_usa_winners[prop_usa_winners["usa_born_winner"] == prop_usa_winners["usa_born_winner"].max()]["decade"].values[0]
print(max_decade_usa)

ax1 = sns.relplot(x="decade", y="usa_born_winner", data=prop_usa_winners, kind="line")

# is_female (alternative_way)
nobel_data["female_winner"] = nobel_data["sex"] == "Female"
print(nobel_data["female_winner"].head())

prop_female_winners = nobel_data.groupby(["decade", "category"], as_index=False)['female_winner'].mean()
print(prop_female_winners.head())

max_female_decade_category = prop_female_winners[prop_female_winners["female_winner"] == prop_female_winners["female_winner"].max()][["decade", "category"]]
print(max_female_decade_category)

max_female_dict = {max_female_decade_category["decade"].values[0]: max_female_decade_category["category"].values[0]}
print(max_female_dict)

ax2 = sns.relplot(x="decade", y="female_winner", hue="category", data=prop_female_winners, kind="line")

# first woman (alternative way)
nobel_women = nobel_data[nobel_data['female_winner']]
print(nobel_women.head())

min_row = nobel_women[nobel_women["year"] == nobel_women["year"].min()]
print(min_row)

first_woman_name = min_row["full_name"].values[0]
print(first_woman_name)

first_woman_category = min_row["category"].values[0]
print(first_woman_category)

print(f"\n The first woman to win a Nobel Prize was {first_woman_name}, in the category of {first_woman_category}.")

# more than 1 time (alternative way)
counts = nobel_data["full_name"].value_counts()
print(counts)

repeats = counts[counts >= 2].index
print(repeats)

repeat_list = list(repeats)
print(repeat_list)

print(f"\n The repeat winners are:", ", ".join(repeat_list))