#!/usr/bin/env python
# coding: utf-8

# In[97]:


import matplotlib.pyplot as plt


# In[106]:


from collections import Counter
c = Counter((w for l in open("train.txt") for w in l.strip().split() if w != "<unk>"))


# In[124]:


#lp = l.strip().split()
ngrams = Counter((w for l in open("train.txt") for lp in [l.strip().split()] for w in zip(lp, lp[1:], lp[2:]) if w != "<unk>"))


# In[4]:


get_ipython().run_line_magic('matplotlib', 'inline')


# In[5]:


import numpy as np
ls = np.array([n for _, n in c.most_common(1000)])
words = [w for w, _ in c.most_common(1000)]


# In[111]:


hist = [0]*100000
for w, k in c.most_common():
    #print k
    hist[k] += 1


# In[125]:


nhist = [0]*100000
for w, k in ngrams.most_common():
    #print k
    nhist[k] += 1


# In[114]:


hist[:10]


# In[134]:


#plt.plot(ls[:200])
sns.set_context("talk", rc={"lines.linewidth": 2.5})
sns.set_style("darkgrid")
f, ax = plt.subplots(figsize=(15, 7))

#plt.plot(figsize=(10,10))
g = sns.barplot(y="total", x="abbrev", data={"total": nhist[1:20], "abbrev": range(1,20)},
            label="Total")
#g.get_axes()[0].set_yscale('log')
g.set( yscale="log")

#_ = ax.set_yticklabels([ w if i % 10 ==0 else "" for i, w in enumerate(words[:200]) ])
plt.savefig("nhist.png")


# In[121]:


#plt.plot(ls[:200])
sns.set_context("talk", rc={"lines.linewidth": 2.5})
sns.set_style("darkgrid")
f, ax = plt.subplots(figsize=(15, 7))

#plt.plot(figsize=(10,10))
sns.barplot(y="total", x="abbrev", data={"total": hist[6:50], "abbrev": range(6,50)},
            label="Total")
#_ = ax.set_yticklabels([ w if i % 10 ==0 else "" for i, w in enumerate(words[:200]) ])
plt.savefig("hist.png")


# In[78]:


#plt.plot(ls[:200])
sns.set_context("talk", rc={"lines.linewidth": 2.5})
sns.set_style("darkgrid")
f, ax = plt.subplots(figsize=(10, 7))

#plt.plot(figsize=(10,10))
sns.barplot(x="total", y="abbrev", data={"total": ls[:200], "abbrev": words[:200]},
            label="Total")
_ = ax.set_yticklabels([ w if i % 10 ==0 else "" for i, w in enumerate(words[:200]) ])
plt.savefig("zipf.png")


# In[12]:


import seaborn as sns


# In[19]:


y


# In[94]:


import math
x = np.linspace(-5, 5, 1000)
y = x * x * x
plt.plot(x, y)
#plt.gcf().subplots_adjust(top=0.75)
plt.ylim(-5.2, 5.2)
plt.xlim(-5, 5)
plt.savefig("cube.png")


# In[96]:


y2 = np.gradient(y)
plt.plot(x, 100*y2)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)
plt.ylim(-0.2, 5.2)
#plt.xlim(-5, 5)


plt.savefig("cubegrad.png")


# In[85]:


x = np.linspace(-5, 5, 1000)
y = np.tanh(x)
plt.plot(x, y)
#plt.gcf().subplots_adjust(top=0.75)
plt.ylim(-1.2, 1.2)
plt.xlim(-5, 5)

#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.savefig("tanh.png")


# In[87]:


y2 = np.gradient(y)
plt.plot(x, 100*y2)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)
plt.ylim(-0.2, 1.2)
#plt.xlim(-5, 5)


plt.savefig("tanhgrad.png")


# In[82]:


x = np.linspace(-5, 5, 1000)
y = np.maximum(-1, x)
y = np.minimum(1, y)
plt.plot(x, y)
#plt.gcf().subplots_adjust(top=0.75)
plt.ylim(-1.2, 1.2)
plt.xlim(-5, 5)


#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.savefig("hardtanh.png")


# In[83]:


y2 = np.gradient(y)
plt.plot(x, 100*y2)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)

plt.savefig("hardtanhgrad.png")


# In[79]:


x = np.linspace(-5, 5, 1000)
y = 1./(1 + np.exp(-x)) 
plt.plot(x, y)
#plt.gcf().subplots_adjust(top=0.75)
plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)


#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.savefig("sigmoid.png")


# In[80]:


y2 = np.gradient(y)
plt.plot(x,100*y2)
plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)

plt.savefig("sigmoidgrad.png")


# In[7]:


import IPython
IPy


# In[75]:


x = np.linspace(-5, 5, 1000)

y = np.array([max(a, 0) for a in list(x)])
plt.plot(x, y)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.ylim(-0.2, 5)
plt.xlim(-5, 5)
plt.savefig("Relu.png")


# In[78]:


y2 = np.gradient(y)
plt.plot(x, y2*100)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)plt.ylim(-0.2, 1.2)
plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)

plt.savefig("Relugrad.png")


# In[71]:


x = np.linspace(-5, 5, 1000)

y = x > 0
plt.plot(x, y)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)
plt.savefig("01.png")


# In[73]:


y2 = np.gradient(y)
plt.plot(x, y2*100)
#sns.regplot(y="y", x="x", data={"x":x, "y":y},  scatter=False, order=5)
plt.ylim(-0.2, 1.2)
plt.xlim(-5, 5)
plt.savefig("01grad.png")