Jorge Valerio - Fab Lab ESAN - Fab Futures - Data Science

Home About

< Home

# Week 1: Tools

Assignment 02

• Visualize your data set(s)

Prepare the environment in Jupyter

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

%matplotlib inline

path = "datasets/Enaho01A-2025-300.csv"
df = pd.read_csv(path, encoding="latin-1")

df.shape
df.columns[:20]

Index(['AÑO', 'MES', 'CONGLOME', 'VIVIENDA', 'HOGAR', 'CODPERSO', 'UBIGEO',
       'DOMINIO', 'ESTRATO', 'CODINFOR', 'P300N', 'P300I', 'P300A', 'P301A',
       'P301B', 'P301C', 'P301D', 'P301A0', 'P301A1', 'P301B0'],
      dtype='object')

df.head()

	AÑO	MES	CONGLOME	VIVIENDA	HOGAR	CODPERSO	UBIGEO	DOMINIO	ESTRATO	CODINFOR	...	I311D$2	I311D$3	I311D$4	I311D$5	I311D$6	I311D$7	I3121C	I3122C	I315B	FACTOR
0	2025	1	15009	12	11	1	10101	4	4	1	...						23				333.512304
1	2025	1	15009	12	11	2	10101	4	4	2	...										380.999876
2	2025	1	15009	25	11	1	10101	4	4	1	...										495.705947
3	2025	1	15009	25	11	2	10101	4	4	2	...										426.265173
4	2025	1	15009	25	11	3	10101	4	4	3	...										380.999876

5 rows × 491 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 24070 entries, 0 to 24069
Columns: 491 entries, AÑO to FACTOR
dtypes: float64(1), int64(19), object(471)
memory usage: 90.2+ MB

df.describe()

	AÑO	MES	CONGLOME	VIVIENDA	HOGAR	CODPERSO	UBIGEO	DOMINIO	ESTRATO	CODINFOR	P300N	P300I	P300A	P301A	P203	P204	P207	P208A	TICUEST01A	FACTOR
count	24070.0	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.00000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.000000	24070.0	24070.000000
mean	2025.0	2.006606	17766.863980	79.493062	11.150519	2.470710	130352.322642	4.85646	4.194267	1.902700	2.470710	1.902700	5.986207	7.521978	2.504279	1.004030	1.514666	37.076651	2.0	1402.106879
std	0.0	0.820961	1627.265031	73.467597	1.404687	1.511061	67535.209034	2.41155	2.436749	1.208535	1.511061	1.208535	14.909601	14.787570	1.699042	0.063355	0.499795	22.669416	0.0	1296.668961
min	2025.0	1.000000	15005.000000	1.000000	11.000000	1.000000	10101.000000	1.00000	1.000000	0.000000	1.000000	0.000000	1.000000	1.000000	1.000000	1.000000	1.000000	3.000000	2.0	39.102612
25%	2025.0	1.000000	16389.000000	31.000000	11.000000	1.000000	70106.000000	2.00000	2.000000	1.000000	1.000000	1.000000	4.000000	3.000000	1.000000	1.000000	1.000000	16.000000	2.0	629.746563
50%	2025.0	2.000000	17697.000000	66.000000	11.000000	2.000000	140102.000000	5.00000	4.000000	2.000000	2.000000	2.000000	4.000000	5.000000	2.000000	1.000000	2.000000	35.000000	2.0	977.814978
75%	2025.0	3.000000	19176.000000	107.000000	11.000000	3.000000	180106.000000	7.00000	7.000000	2.000000	3.000000	2.000000	4.000000	6.000000	3.000000	1.000000	2.000000	55.000000	2.0	1640.860425
max	2025.0	3.000000	20804.000000	871.000000	45.000000	13.000000	250304.000000	8.00000	8.000000	12.000000	13.000000	12.000000	99.000000	99.000000	11.000000	2.000000	2.000000	98.000000	2.0	8758.553932

map_edu = {
    1: "No level of education",
    2: "Early childhood education",
    3: "Incomplete primary education",
    4: "Complete primary education",
    5: "Incomplete secondary education",
    6: "Complete secondary education",
    7: "Incomplete non-university higher education",
    8: "Complete non-university higher education",
    9: "Incomplete university higher education",
    10: "Complete university higher education",
    11: "Master's/Doctoral degree",
    12: "Special basic education"
}

df["level_ed"] = df["P301A"].map(map_edu)

df["region"] = df["UBIGEO"].astype(str).str.zfill(6).str[:2]

regions = {
    "01": "Amazonas", "02": "Áncash", "03": "Apurímac", "04": "Arequipa",
    "05": "Ayacucho", "06": "Cajamarca", "07": "Callao", "08": "Cusco",
    "09": "Huancavelica", "10": "Huánuco", "11": "Ica", "12": "Junín",
    "13": "La Libertad", "14": "Lambayeque", "15": "Lima",
    "16": "Loreto", "17": "Madre de Dios", "18": "Moquegua",
    "19": "Pasco", "20": "Piura", "21": "Puno", "22": "San Martín",
    "23": "Tacna", "24": "Tumbes", "25": "Ucayali"
}

df["region"] = df["region"].map(regions)

table_reg = pd.crosstab(df["level_ed"], df["region"], normalize="columns")*100
table_reg

region	Amazonas	Apurímac	Arequipa	Ayacucho	Cajamarca	Callao	Cusco	Huancavelica	Huánuco	Ica	...	Madre de Dios	Moquegua	Pasco	Piura	Puno	San Martín	Tacna	Tumbes	Ucayali	Áncash
level_ed
Complete non-university higher education	6.165228	3.267974	9.278351	4.046997	5.297297	11.094675	6.306306	3.021148	4.081633	9.440880	...	6.265664	15.192744	4.797048	6.239316	3.697749	6.042296	8.016878	7.733813	3.954214	5.440901
Complete primary education	16.646116	11.111111	8.247423	12.402089	17.729730	8.136095	9.523810	12.688822	10.204082	7.516040	...	11.528822	9.523810	16.051661	12.735043	13.826367	16.515609	7.313643	7.553957	11.030177	12.101313
Complete secondary education	14.673243	16.666667	24.554827	15.143603	15.675676	29.437870	18.146718	18.731118	14.285714	26.764436	...	19.047619	19.954649	19.557196	19.487179	22.347267	16.213494	31.223629	25.000000	19.250780	20.075047
Complete university higher education	2.589396	4.084967	8.716026	5.613577	2.270270	7.396450	5.920206	3.172205	5.048335	9.074244	...	5.012531	8.616780	4.243542	4.444444	4.180064	4.632427	7.594937	4.316547	3.537981	5.816135
Early childhood education	4.932182	2.941176	4.592315	4.830287	5.081081	3.402367	2.831403	3.323263	3.974221	4.307974	...	5.513784	2.947846	4.981550	5.641026	2.250804	3.726083	2.812940	4.856115	5.411030	3.377111
Incomplete non-university higher education	2.589396	1.797386	4.404873	2.219321	1.621622	6.360947	2.574003	1.963746	2.363050	5.041247	...	3.258145	3.174603	2.583026	3.846154	3.697749	2.416918	4.078762	2.877698	4.578564	2.814259
Incomplete primary education	26.880395	23.856209	14.714152	24.934726	24.972973	11.834320	21.364221	25.377644	26.638024	13.198900	...	19.298246	12.698413	21.771218	21.196581	23.151125	23.967774	14.205345	20.683453	21.540062	20.919325
Incomplete secondary education	15.659679	15.686275	14.245548	13.577023	14.054054	12.278107	15.444015	15.407855	14.930183	13.932172	...	17.293233	15.192744	14.391144	16.495726	13.183280	15.709970	12.376934	17.625899	20.603538	15.290807
Incomplete university higher education	3.082614	4.738562	5.998126	4.569191	1.513514	5.029586	4.375804	2.870091	5.155747	6.874427	...	4.761905	5.215420	3.690037	2.735043	4.823151	5.035247	5.766526	5.215827	3.642040	5.065666
Master's/Doctoral degree	0.493218	0.326797	2.061856	0.783290	0.540541	1.479290	1.801802	0.453172	3.222342	1.008249	...	1.002506	2.040816	0.369004	0.769231	1.125402	1.007049	1.406470	0.719424	0.416233	1.594747
No level of education	6.165228	15.522876	3.186504	11.879896	11.243243	3.106509	11.583012	12.839879	10.096670	2.199817	...	7.017544	5.442177	7.564576	6.324786	7.717042	4.531722	4.922644	3.237410	6.035380	7.223265
Special basic education	0.123305	0.000000	0.000000	0.000000	0.000000	0.443787	0.128700	0.151057	0.000000	0.641613	...	0.000000	0.000000	0.000000	0.085470	0.000000	0.201410	0.281294	0.179856	0.000000	0.281426

12 rows × 25 columns

plt.figure(figsize=(14,7))
table_reg.T.plot(kind="bar", stacked=True, figsize=(14,7))

plt.title("Educational level attained by region")
plt.ylabel("Percentage (%)")
plt.xlabel("Region")
plt.xticks(rotation=90)
plt.legend(title="Educational level", bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()

<Figure size 1400x700 with 0 Axes>

import seaborn as sns
plt.figure(figsize=(14,8))
sns.heatmap(table_reg, cmap="YlGnBu", linewidths=.5)

plt.title("Educational level heatmap by region")
plt.xlabel("Educational level")
plt.ylabel("Region")
plt.show()