diff --git a/build.py b/build.py index c7d540b..9f5ce6c 100644 --- a/build.py +++ b/build.py @@ -1,22 +1,51 @@ -def get_categorical_variables(df): - return [] +import numpy as np +import pandas as pd +from scipy.stats import norm +import seaborn as sns +import matplotlib.pyplot as plt +df = pd.read_csv('data/employee_retention_data.csv') -def get_numerical_variables(df): - return [] +def get_categorical_variables(df): + categorical_data = list(df[['dept', 'join_date', 'quit_date']]) + return categorical_data +def get_numerical_variables(df): + numeric = pd.DataFrame._get_numeric_data(df) + return list(numeric) def get_numerical_variables_percentile(df): - pass + per = df.describe().T + return per def get_categorical_variables_modes(df): - pass - + return df[get_categorical_variables(df)].mode() def get_missing_values_count(df): - pass + return pd.DataFrame(df.isnull().sum()) def plot_histogram_with_numerical_values(df): - pass + + num_cols = get_numerical_variables(df) + plt.figure(figsize=(15,6)) + + plt.subplot(221) + plt.title(num_cols[0]) + sns.distplot(df[num_cols[0]], color='Blue', fit=norm, kde=False) + + plt.subplot(222) + plt.title(num_cols[1]) + sns.distplot(df[num_cols[1]], color='Blue', fit=norm, kde=False) + + plt.subplot(223) + plt.title(num_cols[2]) + sns.distplot(df[num_cols[2]], color='Blue', fit=norm, kde=False) + + plt.subplot(224) + plt.title(num_cols[3]) + sns.distplot(df[num_cols[3]], color='Blue', fit=norm, kde=False) + + plt.tight_layout() + plt.show() diff --git a/build.pyc b/build.pyc new file mode 100644 index 0000000..c527ec0 Binary files /dev/null and b/build.pyc differ diff --git a/tests/__init__.pyc b/tests/__init__.pyc new file mode 100644 index 0000000..1a0e28f Binary files /dev/null and b/tests/__init__.pyc differ diff --git a/tests/test_get_categorical_variables.pyc b/tests/test_get_categorical_variables.pyc new file mode 100644 index 0000000..17a7515 Binary files /dev/null and b/tests/test_get_categorical_variables.pyc differ