SELECT * FROM 'exams.csv'

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

# 2. Cargar los datos del Dataframe df=pd.read_csv('exams.csv') df

# Las primeras 5 filas df.head()

#Las ultimas 5 filas df.tail()

#Resumen estadistico df.describe()

# 3. Revisar el tipo de datos df.dtypes

# 4. Eliminar los datos 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()

# Cantidad de filas luego de eliminar los duplicados 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 las 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

# Eliminar los valores perdidos o nulos # Encontrar los valores nulos print(df.isnull().sum())

# Eliminar los valores perdidos df = df.dropna() # Despues de eliminar los nulos print(df.isnull().sum())

# 8. Detectar los Outliers sns.boxplot(x=df['Math score'], color='royalblue') plt.show() sns.boxplot(x=df['Physics score'], color='tomato') plt.show() sns.boxplot(x=df['Chemistry score'], color='crimson') plt.show() sns.boxplot(x=df['Algebra score'], color='dodgerblue') 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. Encontrar correlaciones y frecuencias plt.hist(df['Algebra score'], color='dodgerblue', bins=20) plt.title('Algebra') plt.ylabel('Student count') plt.xlabel('Score') plt.show() plt.hist(df['Chemistry score'], color='crimson', bins=20) plt.title('Chemistry') plt.ylabel('Student count') plt.xlabel('Score') plt.show() plt.hist(df['Math score'], color='royalblue', bins=20) plt.title('Math') plt.ylabel('Student count') plt.xlabel('Score') plt.show() plt.hist(df['Physics score'], color='tomato', bins=20) plt.title('Physics') plt.ylabel('Student count') plt.xlabel('Score') plt.show()

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

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

# pandas.value_counts() --> devuelve una serie con valores unicos en orden descendente de frecuencia labels = df['Gender'].value_counts().index sizes = df['Gender'].value_counts() colors = ['tomato', 'royalblue'] plt.pie(sizes, labels = labels, colors = colors, autopct='%1.2f%%') plt.title('Gender') plt.show() #Repetimos para Etnia, Empleo y el resto de las variables categóricas labels = df['Ethnicity'].value_counts().index sizes = df['Ethnicity'].value_counts() colors = ['tomato', 'royalblue', 'dodgerblue', 'coral', 'lightsalmon'] plt.pie(sizes, labels = labels,colors = colors, autopct='%1.2f%%') plt.title('Ethnicity') plt.show() labels = df['Employed'].value_counts().index sizes = df['Employed'].value_counts() colors = ['tomato', 'royalblue'] plt.pie(sizes, labels = labels, colors = colors, autopct='%1.2f%%') plt.title('Is the student employed?') plt.show() labels = df['Test preparation course'].value_counts().index sizes = df['Test preparation course'].value_counts() colors = ['tomato', 'royalblue'] plt.pie(sizes, labels = labels, colors = colors, 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() colors = ['tomato', 'royalblue', 'dodgerblue', 'coral', 'lightsalmon', 'steelblue'] plt.pie(sizes, labels = labels, colors = colors, autopct='%1.2f%%') plt.title('Parental level of education') plt.show() labels = df['Lunch'].value_counts().index sizes = df['Lunch'].value_counts() colors = ['tomato', 'royalblue'] plt.pie(sizes, labels = labels, colors = colors, autopct='%1.2f%%') plt.title('Lunch') plt.show()

df['Average score'] = df.mean(axis=1) # axis=1 hace que aplique 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=.5, fill=True) sns.histplot(no['Average score'], color='red', alpha=.5, fill=True) plt.show()

print('Realizaron el curso: ', si['Test preparation course'].count()) print('No realizaron el curso: ', no['Test preparation course'].count())