In [958]:
import math
import seaborn as sns
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from bs4 import BeautifulSoup
from sklearn.linear_model import LinearRegression
import warnings
# ignore warnings
warnings.filterwarnings('ignore')
# display all rows for tables
pd.set_option("display.max_rows", None, "display.max_columns", None)
child_marriage = pd.read_csv("marriageage.csv")
# filter recent data after 2002
child_marriage_post_2002 = child_marriage[child_marriage.Year > 2002]
count_by_year = child_marriage_post_2002['Year'].value_counts()
# organize grouped data into dataframe with proper column names
df_with_year_count_columns = pd.DataFrame({'Year':count_by_year.index, 'Count':count_by_year.values})
child_marriage_2002 = df_with_year_count_columns.sort_index()
# Create a plot with most data since 2002
plt.figure(figsize = (10, 10))
plt.bar(child_marriage_2002['Year'], child_marriage_2002['Count'])
# label the count values for each year
xlabels = []
for index, row in child_marriage_2002.iterrows():
plt.text(row.Year, row.Count, row.Count, ha = 'center', bbox = dict(facecolor = 'red', alpha =0.8))
xlabels.append(row.Year)
ax = plt.subplot()
ax.set_xticks(child_marriage_2002['Year'])
ax.set_xticklabels(xlabels)
plt.title("Number of data for each year")
plt.xlabel("Year")
plt.ylabel("Count")
child_marriage_2010 = child_marriage[child_marriage.Year == 2010]
child_marriage_2010 = child_marriage_2010.rename(columns={'Estimated average age at marriage, women': 'MarriageAge'})
child_marriage_2010 = child_marriage_2010.sort_values(by=['MarriageAge'])
child_marriage_2010 = child_marriage_2010.drop(columns=['Year'])
