import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import os

bautismos_path = "../data/clean/bautismos_clean.csv"
entierros_path = "../data/clean/entierros_clean.csv"
matrimonios_path = "../data/clean/matrimonios_clean.csv"

bautismos = pd.read_csv(bautismos_path)
entierros = pd.read_csv(entierros_path)
matrimonios = pd.read_csv(matrimonios_path)

os.makedirs("../figures", exist_ok=True)

def prepare_events(df, sacrament_label):
    df = df.copy()
    df["event_date"] = pd.to_datetime(df["event_date"], errors="coerce")
    df = df.dropna(subset=["event_date"])
    df["year"] = df["event_date"].dt.year
    df["sacrament"] = sacrament_label
    return df[["year", "sacrament"]]

bautismos_yearly = prepare_events(bautismos, "Baptisms")
entierros_yearly = prepare_events(entierros, "Burials")
matrimonios_yearly = prepare_events(matrimonios, "Marriages")

events_all = pd.concat(
    [bautismos_yearly, entierros_yearly, matrimonios_yearly],
    ignore_index=True
)

yearly_counts = (
    events_all
    .groupby(["year", "sacrament"])
    .size()
    .reset_index(name="count")
)

yearly_pivot = yearly_counts.pivot(index="year", columns="sacrament", values="count")

yearly_pivot = yearly_pivot.fillna(0).sort_index()


years = yearly_pivot.index.values
cols  = yearly_pivot.columns

fig, ax = plt.subplots()

bottom = np.zeros(len(years))  

for sacrament in cols:
    counts = yearly_pivot[sacrament].values
    ax.bar(
        years,
        counts,
        bottom=bottom,
        label=sacrament
    )
    bottom += counts  

ax.set_xlabel("Year")
ax.set_ylabel("Number of events")
ax.legend(title="Event Type")

plt.tight_layout()
plt.show()

fig.savefig("../figures/distribution_events_per_year.png", dpi=300)

personas = pd.read_csv("../data/clean/personas.csv")
places = pd.read_csv("../data/clean/places.csv")

/var/folders/37/816y3tg93hn7pnnrd0c33c_00000gn/T/ipykernel_80252/254567552.py:1: DtypeWarning: Columns (13,14,15) have mixed types. Specify dtype option on import or set low_memory=False.
  personas = pd.read_csv("../data/clean/personas.csv")

places['place_name'] = places['place_name'].str.strip().str.lower()
birth_places = personas.merge(places, left_on='birth_place', right_on='place_name', how='left')

birth_places = birth_places.dropna(subset=['latitude', 'longitude'])
birth_places = birth_places[['birth_place', 'latitude', 'longitude']]

birth_places_count = birth_places.groupby(['birth_place', 'latitude', 'longitude']).size().reset_index(name='count')
birth_places_count.sort_values('count', ascending=False, inplace=True)

birth_places_count.to_csv("../data/stats/birth_places_count.csv", index=False)

birth_places_count.describe()

	latitude	longitude	count
count	72.000000	72.000000	72.000000
mean	-14.108773	-74.204983	76.222222
std	0.508643	0.560368	305.530304
min	-15.278870	-76.484250	1.000000
25%	-14.286957	-74.274407	1.000000
50%	-14.177605	-74.036060	2.000000
75%	-13.922675	-73.944478	5.000000
max	-11.775270	-73.185060	1903.000000

birth_places_count

	birth_place	latitude	longitude	count
52	pampamarca	-14.23274	-74.04139	1903
4	aucará	-14.28099	-73.97489	1505
15	chacralla	-14.20690	-73.99316	845
38	ishua	-14.24973	-73.95556	640
62	santa ana de aucará	-14.19929	-74.08823	108
...	...	...	...	...
39	jauja	-11.77527	-75.50007	1
40	julcamarca	-13.01443	-74.44459	1
45	nasca	-14.82763	-74.93700	1
46	ocaña	-14.39862	-74.82269	1
71	yanaccollpa	-14.54731	-74.26170	1

72 rows × 4 columns

most_places = sum([1903,1505,845,640])
most_places

4893

perc = most_places * 100 / birth_places_count['count'].sum()
perc.round(0)

np.float64(89.0)