Created
February 16, 2021 03:47
-
-
Save ksv-muralidhar/ddc07a2c884912395dfe2cfce2a6c2ec to your computer and use it in GitHub Desktop.
EDA
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.datasets import load_diabetes | |
import numpy as np | |
import pandas as pd | |
import matplotlib.pyplot as plt | |
import seaborn as sns | |
# LOADING DIABETES DATA (INPUT FEATURES) AND STORING IT IN A DATA FRAME | |
data = pd.DataFrame(load_diabetes()["data"],columns=load_diabetes()["feature_names"]) | |
#ADDING TARGET VARIABLE TO THE DATA FRAME | |
data["target"] = load_diabetes()["target"] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
numeric_features = list(data.select_dtypes("float64").columns) | |
numeric_features.remove('target') | |
categorical_features = list(data.select_dtypes("int8").columns) | |
target = "target" | |
print(f'numeric_features:\n{numeric_features}\n\ncategorical_features:\n{categorical_features}\n\ntarget:\n{target}') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
np.round(data.isnull().mean() * 100,1) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
for i in categorical_features: | |
print(f'{i}\n{np.round((data[i].value_counts() / data[i].value_counts().sum()) * 100,2)}') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fig,ax = plt.subplots(3,3,figsize=(10,10)) | |
row = col = 0 | |
for n,i in enumerate(numeric_features): | |
if (n%3 == 0) & (n > 0): | |
row += 1 | |
col = 0 | |
data[i].plot(kind="kde",ax=ax[row,col]) | |
ax[row,col].set_title(i) | |
col += 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from scipy.stats import normaltest | |
for i in numeric_features: | |
print(f'{i}: {"Not Gaussian" if normaltest(data[i].values,)[1]<0.05 else "Gaussian"} {normaltest(data[i].values)}') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
for i in numeric_features: | |
print(f'{i}: {np.abs(np.round((data[i].std()/data[i].median()) * 100,2))}') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fig,ax = plt.subplots(1,3,figsize=(20,5)) | |
data[target].plot(kind="hist",ax=ax[0]) | |
data[target].plot(kind="kde",ax=ax[1]) | |
data[target].plot(kind="box",ax=ax[2]) | |
plt.show() | |
print(f'{target}: {"Not Gaussian" if normaltest(data[target].values,)[1]<0.05 else "Gaussian"} {normaltest(data[target].values)}') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sns.boxplot(x=data[categorical_features[0]],y=data[target]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fig,ax = plt.subplots(3,3,figsize=(15,10)) | |
row = col = 0 | |
for n,i in enumerate(numeric_features): | |
if (n%3 == 0) & (n > 0): | |
row += 1 | |
col = 0 | |
sns.regplot(x=i,y="target",data=data,ax=ax[row,col],ci=False) | |
col += 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
num_tgt = numeric_features.copy() | |
num_tgt.append('target') | |
fig = plt.figure(figsize=(8,8)) | |
sns.heatmap(data[num_tgt].corr(method='pearson'),annot=True,fmt='.2f',mask=np.triu(data[num_tgt].corr(method='pearson')),cbar=False) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data.shape |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fig = plt.figure(figsize=(8,8)) | |
sns.heatmap(data[num_tgt].corr(method='kendall'),annot=True,fmt='.2f',mask=np.triu(data[num_tgt].corr(method='pearson')),cbar=False) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data.head() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
list(data.columns) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data.dtypes |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data["sex"].unique() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data.loc[data["sex"]>0,"sex"] = 1 | |
data.loc[data["sex"]<0,"sex"] = 0 | |
data.head() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data.describe().T |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data["sex"] = data["sex"].astype(np.int8) | |
data.dtypes |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment