Python Libraries for Data Analysis¶

import pandas as pd
df = pd.read_csv('data.csv')
df.groupby('country')['revenue'].sum()

import numpy as np
a = np.array([1, 2, 3])
np.mean(a); np.std(a); np.percentile(a, 95)

import matplotlib.pyplot as plt
plt.plot(x, y); plt.xlabel('Date'); plt.ylabel('Revenue'); plt.show()

import seaborn as sns
sns.boxplot(data=df, x='category', y='revenue')
sns.heatmap(df.corr(), annot=True)
sns.pairplot(df)

import plotly.express as px
px.scatter(df, x='ad_spend', y='revenue', color='channel', size='clicks')

from scipy import stats
stats.ttest_ind(group_a, group_b)
stats.pearsonr(x, y)
stats.zscore(arr)

import statsmodels.api as sm
X = sm.add_constant(df[['x1', 'x2']])
model = sm.OLS(df['y'], X).fit()
print(model.summary())

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = LogisticRegression().fit(X_train, y_train)
model.score(X_test, y_test)