Trabajo Práctico Integrador

# 1. Importar las librerías import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt

# 2. Cargar los datos en el dataframe df = pd.read_csv('/work/exams.csv') df

# Primeras 5 filas df.head()

# Últimas filas df.tail()

# Resumen estadístico df.describe()

# Tipos de Datos df.dtypes

# 4. Eliminar los duplicados print(f'Original: {df.id.count()}filas') duplicate_rows_df = df[df.duplicated()] print(f'Cantidad de filas duplicadas: {duplicate_rows_df.id.count()}') #Eliminar los duplicados df = df.drop_duplicates()

#Filas restantes print(f'Final: {df.id.count()}filas')

# 5. Eliminar las columnas irrelevantes print(df.columns) df = df.drop(['id'], axis=1)

print(df.columns)

# 6. Renombrar Columnas df = df.rename(columns= { "gender":"Gender", "race/ethnicity":"Ethnicity", "parental level of education":"Parental level of education", "lunch":"Lunch", "employed":"Employed", "test preparation course":"Test preparation course", "math score":"Math score", "physics score":"Physics score", "chemistry score":"Chemistry score", "algebra_score":"Algebra_score" }) df.columns

# Encontras y eliminar los valores perdidos o nulos print(df.isnull().sum()) df = df.dropna()

#8. Detectar los outliers sns.boxplot(x=df['Math score']) plt.show() sns.boxplot(x=df['Physics score']) plt.show() sns.boxplot(x=df['Algebra_score']) plt.show() sns.boxplot(x=df['Chemistry score']) plt.show()

print(f'Antes: {df.Lunch.count()} filas/n') Q1 = df.quantile(0.25) Q3 = df.quantile(0.75) IQR = Q3 - Q1 print(IQR) df = df[~((df < (Q1-1.5 * IQR)) | (df > (Q3 + 1.5 * IQR))).any(axis=1)] print(f'/nDespués: {df.Lunch.count()} filas')

# 9. Encontras correlaciones y frecuencias plt.hist(df['Algebra_score'], bins=20) plt.title("Algebra") plt.ylabel("Student count") plt.xlabel("Score") plt.show() plt.hist(df['Chemistry score'], bins=20) plt.title("Chemistry") plt.ylabel("Student count") plt.xlabel("Score") plt.show() plt.hist(df['Math score'], bins=20) plt.title("Math") plt.ylabel("Student count") plt.xlabel("Score") plt.show() plt.hist(df['Physics score'], bins=20) plt.title("Physics") plt.ylabel("Student count") plt.xlabel("Score") plt.show()

# Correlación entre los datos = Mapas de calor c = df.corr() print(c)

plt.figure(figsize=(20,10)) sns.heatmap(c,cmap="BrBG",annot=True) plt.show()

# pandas.value_counts() - Devuelve Serie de valores únicos en orden descendente de frecuencia labels = df["Gender"].value_counts().index sizes = df["Gender"].value_counts() plt.pie(sizes, labels=labels, autopct='%1.2f%%') plt.title('Gender') plt.show() labels = df["Ethnicity"].value_counts().index sizes = df["Ethnicity"].value_counts() plt.pie(sizes, labels=labels, autopct='%1.2f%%') plt.title('Ethnicity') plt.show() labels = df["Employed"].value_counts().index sizes = df["Employed"].value_counts() plt.pie(sizes, labels=labels, autopct='%1.2f%%') plt.title('Employed') plt.show() labels = df["Test preparation course"].value_counts().index sizes = df["Test preparation course"].value_counts() plt.pie(sizes, labels=labels, autopct='%1.2f%%') plt.title('Test preparation course') plt.show() labels = df["Parental level of education"].value_counts().index sizes = df["Parental level of education"].value_counts() plt.pie(sizes, labels=labels, autopct='%1.2f%%') plt.title('Parental level of education') plt.show() labels = df["Lunch"].value_counts().index sizes = df["Lunch"].value_counts() plt.pie(sizes, labels=labels, autopct='%1.2f%%') plt.title('Lunch') plt.show()

df['Average Score'] = df.mean(axis = 1) #axis = 1 hace que aploque la función sobre los valores numéricos de la fila en lugar de las columnas df

si = df[df['Test preparation course']== 'completed'] no = df[df['Test preparation course']== 'none']

sns.histplot(si['Average Score'], color = 'blue', alpha=.4, fill=True) sns.histplot(no['Average Score'], color = 'red', alpha=.4, fill=True) plt.show()