In [1]:
from google.colab import files
uploaded = files.upload()
In [2]:
import sys
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [3]:
st = pd.read_csv('school_totals_nv_2019.csv')
In [4]:
st
Out[4]:
In [5]:
st.shape
Out[5]:
In [6]:
st.columns
Out[6]:
In [7]:
st.index
Out[7]:
In [8]:
st_w_header = pd.read_csv('school_totals_nv_2019.csv', header=None)
In [9]:
st_w_header
Out[9]:
In [10]:
st.iloc[0]
Out[10]:
In [11]:
st.iloc[1]
Out[11]:
In [12]:
st.iloc[-1]
Out[12]:
In [13]:
st.iloc[:,0]
Out[13]:
In [14]:
st.iloc[:,1]
Out[14]:
In [15]:
st.iloc[0:, -1]
Out[15]:
In [16]:
st.iloc[0:5]
Out[16]:
In [17]:
st.iloc[:,0:2]
Out[17]:
In [18]:
st.iloc[0:5, 3:5]
Out[18]:
In [19]:
st.iloc[[0,1,2,3],[2,3,5]]
Out[19]:
In [20]:
st_sorted = st.sort_values(by='Total',ascending=False)
In [21]:
st_sorted
Out[21]:
In [22]:
st_top7=st_sorted.head(7)
In [23]:
st_top7
Out[23]:
In [24]:
st_top7['School Name']
Out[24]:
In [25]:
st_top7['School Name'].values
Out[25]:
In [26]:
import seaborn as sns
sns.set()
plt.figure(figsize=(10,6))
plt.bar(x=st_top7['School Name'], height=st_top7['Total'], color='rgbymcw')
plt.xticks(rotation=45)
plt.title('The Top Seven Highest Enrollment Schools in Nevada in 2019')
Out[26]:
In [27]:
st.columns
Out[27]:
In [28]:
st['Total'].sum()
Out[28]:
In [29]:
st.loc[0]
Out[29]:
In [30]:
st.loc[1]
Out[30]:
In [31]:
st.loc[1, 'Total']
Out[31]:
In [32]:
st.loc[st.Total>3000]
Out[32]:
In [33]:
clark = st.loc[st['Master District Name']=='Clark']
In [34]:
clark
Out[34]:
In [35]:
clark_sorted = clark.sort_values(['Total'], ascending=False)
In [36]:
clark_sorted
Out[36]:
In [37]:
clark['Total'].sum()
Out[37]:
In [38]:
clark_top7 = clark_sorted.head(7)
In [39]:
clark_top7
Out[39]:
In [40]:
import seaborn as sns
sns.set()
plt.figure(figsize=(10,6))
plt.bar(x=clark_top7['School Name'], height=clark_top7['Total'], color='rgbymcw')
plt.xticks(rotation=45)
plt.title('The Top Seven Highest Enrollment Schools in Clark County in 2019')
Out[40]:
In [41]:
order = [1,2,3,4,5,6,7]
clark_top7_df = pd.DataFrame(clark_top7, columns=['School Name','Total'])
clark_top7_df['order']=order
clark_top7_insert =pd.DataFrame(clark_top7_df, columns=['order','School Name','Total'])
clark_top7_insert
Out[41]:
In [42]:
clark_top7_insert.rename(columns={'School Name':'school_name', 'Total':'total'})
Out[42]:
In [43]:
clark_top7_new = clark_top7_insert.set_index('order')
clark_top7_new
Out[43]:
In [44]:
clark_top7
Out[44]:
In [45]:
clark_1 = clark_top7.loc[[345, 305, 326], ['School Name','Total']]
clark_1
Out[45]:
In [48]:
clark2 = clark_top7.loc[345]
clark2
Out[48]:
In [49]:
clark3 = clark_top7.loc[345:328]
clark3
Out[49]:
In [51]:
clark4 = clark_top7.loc[345:328, ['School Name']]
clark4
Out[51]:
In [52]:
clark5 = clark_top7.loc[:, ['School Name','Total']]
clark5
Out[52]:
In [54]:
clark6 = clark_top7.loc[clark_top7['School Name']=='Coronado']
clark6
Out[54]:
In [58]:
clark7 = st.loc[st['School Name']=='Clark', ['School Name','Total']]
clark7
Out[58]: