# Data manipulation !pip install pandas import pandas as pd

# Data visualization !pip install seaborn import seaborn as sns #Data visualization !pip install matplotlib import matplotlib.pyplot as plt

df = pd.read_csv('MiningProcess_Flotation_Plant_Database.csv')

df.head()

df = pd.read_csv('MiningProcess_Flotation_Plant_Database.csv',decimal=',')

df.head()

df.shape

df['% Iron Concentrate']

df.iloc[100:105,:]

print(type(df))

print(type(df['date']))

print(type(df['date'][0]))

df['date'] = pd.to_datetime(df['date'])

print(type(df['date']))

print(type(df['date'][0]))

df.describe()

max_date=df['date'].max() print('The max date is' + str(max_date)) min_date=df['date'].min() print('The min date is' + str(min_date))

df_june = df[(df['date'] > "2017-05-31 23:59:59") & (df['date'] < "2017-06-02")].reset_index(drop=True)

important_cols = [ 'date', '% Iron Concentrate', '% Silica Concentrate', 'Ore Pulp pH', 'Flotation Column 05 Level' ] df_june_important = df_june[important_cols] df_june_important

sns.pairplot(df_june_important)

df_june_important.corr()

sns.lineplot(x='date',y='% Iron Concentrate',data=df_june)

for i in important_cols: sns.lineplot(x='date',y=i,data=df_june) import matplotlib.pyplot as plt plt.show()

sns.histplot(df_june['Ore Pulp pH'])

sns.scatterplot(x='% Iron Feed',y='Flotation Column 05 Level', data=df_june, size='% Iron Concentrate', legend=False, sizes=(1, 100))

df