import matplotlib.pyplot as plt
import seaborn as sns
from greyatomlib import pandas as pd
data = pd.read_csv('data/house_prices_multivariate.csv')
def plot(num_cols):
for i in range(0, len(num_cols), 2):
if len(num_cols) > i + 1:
plt.figure(figsize=(10, 4))
plt.subplot(121)
sns.distplot(data[num_cols[i]], kde=False)
plt.subplot(122)
sns.distplot(data[num_cols[i + 1]], kde=False)
plt.tight_layout()
plt.show()
else:
sns.distplot(data[num_cols[i]], kde=False)
import scipy.stats as stats
from greyatomlib import pandas as pd
df = pd.read_csv('data/house_pricing.csv')
def chi2_test(df=df):
price = pd.qcut(df['SalePrice'], 3, labels=['High', 'Medium', 'Low'])
freqtab = pd.crosstab(df['LandSlope'], price)
chi2, pval, dof, expected = stats.chi2_contingency(freqtab)
return pval, pval < 0.05
# Default Import
from greyatomlib import pandas as pd
dataframe_1 = pd.read_csv('data/house_prices_multivariate.csv')
house_price = dataframe_1.loc[:, 'SalePrice']
dataframe_2 = pd.read_csv('data/house_prices_copy.csv').loc[:, 'SalePrice']
weight_of_nasa_space_shuttle = dataframe_2.loc[:, 'SalePrice']
def spearman_correlation():
return dataframe_1.SalePrice.corr(dataframe_2.SalePrice, method='spearman')
print(spearman_correlation())
def read_csv_data_to_df(path):
return pd.read_csv(path)
def load_data(path):
dataframe = pd.read_csv(path,index_col=0)
return dataframe